Daily Papers

Living systems face both environmental complexity and limited access to free-energy resources. Survival under these conditions requires a control system that can activate, or deploy, available perception and action resources in a context specific way. We show here that when systems are described as executing active inference driven by the free-energy principle (and hence can be considered Bayesian prediction-error minimizers), their control flow systems can always be represented as tensor networks (TNs). We show how TNs as control systems can be implmented within the general framework of quantum topological neural networks, and discuss the implications of these results for modeling biological systems at multiple scales.

Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However, efficient LLM inference on CPUs faces two fundamental challenges: (1) existing CPU architectures struggle with low-precision arithmetic required by quantized models, where optimal bit precision varies across models and layers; and (2) the memory-bound nature of the token generation phase creates severe performance bottlenecks. To address these challenges, we propose SAIL (SRAM-Accelerated Inference of LLMs), a CPU-based inference solution that efficiently supports arbitrary bit precisions with minimal overhead. SAIL integrates three key innovations: First, we introduce Batched LUT-based General Matrix-Vector Multiplication (LUT-GEMV) with SRAM-based processing-in-memory, enabling high data reuse through lookup tables and reducing memory movement. Second, our Pattern-Aware LUT optimization identifies and exploits redundancy in input activation patterns, reducing computation cycles by 13.8\%. Third, we develop an in-memory type conversion algorithm that leverages PIM's parallelism for efficient de-/quantization operations, alleviating pressure on CPU's vector units. Our architecture requires only 2\% hardware overhead and a single new instruction, while maintaining dual functionality as both compute and storage units. Experimental evaluations using a modified gem5 simulator demonstrate that SAIL achieves up to 10.7x speedup and 19.9x higher tokens per dollar compared to ARM Neoverse-N1 CPU baselines, and up to 7.04x better cost efficiency than NVIDIA V100 GPUs, establishing a practical path for efficient CPU-based LLM inference.

Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a progressive inference paradigm over cloud and edge, i.e., firstly generating the sketch of the answer by LLMs at cloud, and then conducting parallel extension to fill in details by small models (SLMs) at edge. Progressive inference offers potential benefits to improve throughput and reduce inference latency while facing key implementation challenges, including decreased response quality from SLMs, a tradeoff between the brevity and comprehensiveness of sketches, as well as increased latency caused by network transmission and edge inference. In this work, we propose and implement PICE, an LLM serving system with semantic-level cloud-edge collaboration, enhancing inference throughput and quality through dynamic inference task scheduling, ensemble learning, and parallel edge inference. Extensive testbed experiments illustrate that our approach achieves 1.5-2times throughput enhancement and up to 43% latency reduction, while also potentially enhancing the quality compared to SOTA systems.

Large transformer models display promising performance on a wide range of natural language processing (NLP) tasks. Although the AI community has expanded the model scale to the trillion parameter level, the practical deployment of 10-100 billion parameter models is still uncertain due to the latency, throughput, and memory constraints. In this paper, we proposed EnergonAI to solve the challenges of the efficient deployment of 10-100 billion parameter transformer models on single- or multi-GPU systems. EnergonAI adopts a hierarchy-controller system architecture to coordinate multiple devices and efficiently support different parallel patterns. It delegates the execution of sub-models to multiple workers in the single-controller style and applies tensor parallelism and pipeline parallelism among the workers in a multi-controller style. Upon the novel architecture, we propose three techniques, i.e. non-blocking pipeline parallelism, distributed redundant computation elimination, and peer memory pooling. EnergonAI enables the users to program complex parallel code the same as a serial one. Compared with the FasterTransformer, we have proven that EnergonAI has superior performance on latency and throughput. In our experiments, EnergonAI can achieve 37% latency reduction in tensor parallelism, 10% scalability improvement in pipeline parallelism, and it improves the model scale inferred on a single GPU by using a larger heterogeneous memory space at cost of limited performance reduction.

Online inference is becoming a key service product for many businesses, deployed in cloud platforms to meet customer demands. Despite their revenue-generation capability, these services need to operate under tight Quality-of-Service (QoS) and cost budget constraints. This paper introduces KAIROS, a novel runtime framework that maximizes the query throughput while meeting QoS target and a cost budget. KAIROS designs and implements novel techniques to build a pool of heterogeneous compute hardware without online exploration overhead, and distribute inference queries optimally at runtime. Our evaluation using industry-grade deep learning (DL) models shows that KAIROS yields up to 2X the throughput of an optimal homogeneous solution, and outperforms state-of-the-art schemes by up to 70%, despite advantageous implementations of the competing schemes to ignore their exploration overhead.

Serving large language models (LLMs) in production can incur substantial costs, which has prompted recent advances in inference system optimizations. Today, these systems are evaluated against conventional latency and throughput metrics (eg. TTFT, TBT, Normalised Latency and TPOT). However, these metrics fail to fully capture the nuances of LLM inference, leading to an incomplete assessment of user-facing performance crucial for real-time applications such as chat and translation. In this paper, we first identify the pitfalls of current performance metrics in evaluating LLM inference systems. We then propose Etalon, a comprehensive performance evaluation framework that includes fluidity-index -- a novel metric designed to reflect the intricacies of the LLM inference process and its impact on real-time user experience. Finally, we evaluate various existing open-source platforms and model-as-a-service offerings using Etalon, discussing their strengths and weaknesses. Etalon is available at https://github.com/project-etalon/etalon.

A key challenge in eXplainable Artificial Intelligence is the well-known tradeoff between the transparency of an algorithm (i.e., how easily a human can directly understand the algorithm, as opposed to receiving a post-hoc explanation), and its accuracy. We report on the design of a new deep network that achieves improved transparency without sacrificing accuracy. We design a deep convolutional neuro-fuzzy inference system (DCNFIS) by hybridizing fuzzy logic and deep learning models and show that DCNFIS performs as accurately as existing convolutional neural networks on four well-known datasets and 3 famous architectures. Our performance comparison with available fuzzy methods show that DCNFIS is now state-of-the-art fuzzy system and outperforms other shallow and deep fuzzy methods to the best of our knowledge. At the end, we exploit the transparency of fuzzy logic by deriving explanations, in the form of saliency maps, from the fuzzy rules encoded in the network to take benefit of fuzzy logic upon regular deep learning methods. We investigate the properties of these explanations in greater depth using the Fashion-MNIST dataset.

With the increasing diversity of ML infrastructures nowadays, distributed training over heterogeneous computing systems is desired to facilitate the production of big models. Mixture-of-Experts (MoE) models have been proposed to lower the cost of training subject to the overall size of models/data through gating and parallelism in a divide-and-conquer fashion. While DeepSpeed has made efforts in carrying out large-scale MoE training over heterogeneous infrastructures, the efficiency of training and inference could be further improved from several system aspects, including load balancing, communication/computation efficiency, and memory footprint limits. In this work, we present SE-MoE that proposes Elastic MoE training with 2D prefetch and Fusion communication over Hierarchical storage, so as to enjoy efficient parallelisms in various types. For scalable inference in a single node, especially when the model size is larger than GPU memory, SE-MoE forms the CPU-GPU memory jointly into a ring of sections to load the model, and executes the computation tasks across the memory sections in a round-robin manner for efficient inference. We carried out extensive experiments to evaluate SE-MoE, where SE-MoE successfully trains a Unified Feature Optimization (UFO) model with a Sparsely-Gated Mixture-of-Experts model of 12B parameters in 8 days on 48 A100 GPU cards. The comparison against the state-of-the-art shows that SE-MoE outperformed DeepSpeed with 33% higher throughput (tokens per second) in training and 13% higher throughput in inference in general. Particularly, under unbalanced MoE Tasks, e.g., UFO, SE-MoE achieved 64% higher throughput with 18% lower memory footprints. The code of the framework will be released on: https://github.com/PaddlePaddle/Paddle.

The surge in generative AI workloads has created a need for scalable inference systems that can flexibly harness both GPUs and specialized accelerators while containing operational costs. This paper proposes a hardware-agnostic control loop that adaptively allocates requests across heterogeneous accelerators based on real-time cost and capacity signals. The approach sustains low latency and high throughput by dynamically shifting between cost-optimized and capacity-optimized modes, ensuring the most efficient use of expensive compute resources under fluctuating availability. Evaluated using the Stable Diffusion model, the framework consistently meets latency targets, automatically redirects traffic during capacity shortfalls, and capitalizes on lower-cost accelerators when possible. These results highlight how a feedback-driven deployment strategy, spanning the entire software and hardware stack, can help organizations efficiently scale generative AI workloads while maintaining resilience in the face of limited accelerator capacity.

Large Language Models have revolutionized natural language processing, yet serving them efficiently in data centers remains challenging due to mixed workloads comprising latency-sensitive (LS) and best-effort (BE) jobs. Existing inference systems employ iteration-level first-come-first-served scheduling, causing head-of-line blocking when BE jobs delay LS jobs. We introduce QLLM, a novel inference system designed for Mixture of Experts (MoE) models, featuring a fine-grained, priority-aware preemptive scheduler. QLLM enables expert-level preemption, deferring BE job execution while minimizing LS time-to-first-token (TTFT). Our approach removes iteration-level scheduling constraints, enabling the scheduler to preempt jobs at any layer based on priority. Evaluations on an Nvidia A100 GPU show that QLLM significantly improves performance. It reduces LS TTFT by an average of 65.5times and meets the SLO at up to 7 requests/sec, whereas the baseline fails to do so under the tested workload. Additionally, it cuts LS turnaround time by up to 12.8times without impacting throughput. QLLM is modular, extensible, and seamlessly integrates with Hugging Face MoE models.

This paper presents MoE-Gen, a high-throughput MoE inference system optimized for single-GPU execution. Existing inference systems rely on model-based or continuous batching strategies, originally designed for interactive inference, which result in excessively small batches for MoE's key modules-attention and expert modules-leading to poor throughput. To address this, we introduce module-based batching, which accumulates tokens in host memory and dynamically launches large batches on GPUs to maximize utilization. Additionally, we optimize the choice of batch sizes for each module in an MoE to fully overlap GPU computation and communication, maximizing throughput. Evaluation demonstrates that MoE-Gen achieves 8-31x higher throughput compared to state-of-the-art systems employing model-based batching (FlexGen, MoE-Lightning, DeepSpeed), and offers even greater throughput improvements over continuous batching systems (e.g., vLLM and Ollama) on popular MoE models (DeepSeek and Mixtral) across offline inference tasks. MoE-Gen's source code is publicly available at https://github.com/EfficientMoE/MoE-Gen

Reasoning LLMs such as OpenAI o1, o3 and DeepSeek R1 have made significant progress in mathematics and coding, yet find challenging advanced tasks such as International Mathematical Olympiad (IMO) combinatorics problems, Abstraction and Reasoning Corpus (ARC) puzzles, and Humanity's Last Exam (HLE) questions. We use a diverse inference approach that combines multiple models and methods at test time. We find that verifying mathematics and code problems, and rejection sampling on other problems is simple and effective. We automatically verify correctness of solutions to IMO problems by Lean, and ARC puzzles by code, and find that best-of-N effectively answers HLE questions. Our approach increases answer accuracy on IMO combinatorics problems from 33.3% to 77.8%, accuracy on HLE questions from 8% to 37%, and solves 80% of ARC puzzles that 948 humans could not and 26.5% of ARC puzzles that o3 high compute does not. Test-time simulations, reinforcement learning, and meta-learning with inference feedback improve generalization by adapting agent graph representations and varying prompts, code, and datasets. Our approach is reliable, robust, and scalable, and in the spirit of reproducible research, we will make it publicly available upon publication.

Recently, the Natural Language Inference (NLI) task has been studied for semi-structured tables that do not have a strict format. Although neural approaches have achieved high performance in various types of NLI, including NLI between semi-structured tables and texts, they still have difficulty in performing a numerical type of inference, such as counting. To handle a numerical type of inference, we propose a logical inference system for reasoning between semi-structured tables and texts. We use logical representations as meaning representations for tables and texts and use model checking to handle a numerical type of inference between texts and tables. To evaluate the extent to which our system can perform inference with numerical comparatives, we make an evaluation protocol that focuses on numerical understanding between semi-structured tables and texts in English. We show that our system can more robustly perform inference between tables and texts that requires numerical understanding compared with current neural approaches.

Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demand low job completion time (JCT) for model inference. Existing LLM serving systems use run-to-completion processing for inference jobs, which suffers from head-of-line blocking and long JCT. We present FastServe, a distributed inference serving system for LLMs. FastServe exploits the autoregressive pattern of LLM inference to enable preemption at the granularity of each output token. FastServe uses preemptive scheduling to minimize JCT with a novel skip-join Multi-Level Feedback Queue scheduler. Based on the new semi information-agnostic setting of LLM inference, the scheduler leverages the input length information to assign an appropriate initial queue for each arrival job to join. The higher priority queues than the joined queue are skipped to reduce demotions. We design an efficient GPU memory management mechanism that proactively offloads and uploads intermediate states between GPU memory and host memory for LLM inference. We build a system prototype of FastServe based on NVIDIA FasterTransformer. Experimental results show that compared to the state-of-the-art solution Orca, FastServe improves the average and tail JCT by up to 5.1times and 6.4times, respectively.

Mixture of experts (MoE) models achieve state-of-the-art results in language modeling but suffer from inefficient hardware utilization due to imbalanced token routing and communication overhead. While prior work has focused on optimizing MoE training and decoder architectures, inference for encoder-based MoE models in a multi-GPU with expert parallelism setting remains underexplored. We introduce MoEShard, an inference system that achieves perfect load balancing through tensor sharding of MoE experts. Unlike existing approaches that rely on heuristic capacity factors or drop tokens, MoEShard evenly distributes computation across GPUs and ensures full token retention, maximizing utilization regardless of routing skewness. We achieve this through a strategic row- and column-wise decomposition of expert matrices. This reduces idle time and avoids bottlenecks caused by imbalanced expert assignments. Furthermore, MoEShard minimizes kernel launches by fusing decomposed expert computations, significantly improving throughput. We evaluate MoEShard against DeepSpeed on encoder-based architectures, demonstrating speedups of up to 6.4times in time to first token (TTFT). Our results show that tensor sharding, when properly applied to experts, is a viable and effective strategy for efficient MoE inference.

Statically analyzing dynamically-typed code is a challenging endeavor, as even seemingly trivial tasks such as determining the targets of procedure calls are non-trivial without knowing the types of objects at compile time. Addressing this challenge, gradual typing is increasingly added to dynamically-typed languages, a prominent example being TypeScript that introduces static typing to JavaScript. Gradual typing improves the developer's ability to verify program behavior, contributing to robust, secure and debuggable programs. In practice, however, users only sparsely annotate types directly. At the same time, conventional type inference faces performance-related challenges as program size grows. Statistical techniques based on machine learning offer faster inference, but although recent approaches demonstrate overall improved accuracy, they still perform significantly worse on user-defined types than on the most common built-in types. Limiting their real-world usefulness even more, they rarely integrate with user-facing applications. We propose CodeTIDAL5, a Transformer-based model trained to reliably predict type annotations. For effective result retrieval and re-integration, we extract usage slices from a program's code property graph. Comparing our approach against recent neural type inference systems, our model outperforms the current state-of-the-art by 7.85% on the ManyTypes4TypeScript benchmark, achieving 71.27% accuracy overall. Furthermore, we present JoernTI, an integration of our approach into Joern, an open source static analysis tool, and demonstrate that the analysis benefits from the additional type information. As our model allows for fast inference times even on commodity CPUs, making our system available through Joern leads to high accessibility and facilitates security research.

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the increasing memory footprint and the need to access it for each token generation both result in low throughput when serving long-context LLMs. While various dynamic sparse attention methods have been proposed to speed up inference while maintaining generation quality, they either fail to sufficiently reduce GPU memory consumption or introduce significant decoding latency by offloading the KV cache to the CPU. We present ShadowKV, a high-throughput long-context LLM inference system that stores the low-rank key cache and offloads the value cache to reduce the memory footprint for larger batch sizes and longer sequences. To minimize decoding latency, ShadowKV employs an accurate KV selection strategy that reconstructs minimal sparse KV pairs on-the-fly. By evaluating ShadowKV on a broad range of benchmarks, including RULER, LongBench, and Needle In A Haystack, and models like Llama-3.1-8B, Llama-3-8B-1M, GLM-4-9B-1M, Yi-9B-200K, Phi-3-Mini-128K, and Qwen2-7B-128K, we demonstrate that it can support up to 6times larger batch sizes and boost throughput by up to 3.04times on an A100 GPU without sacrificing accuracy, even surpassing the performance achievable with infinite batch size under the assumption of infinite GPU memory. The code is available at https://github.com/bytedance/ShadowKV.

In recent years, Mixture-of-Experts (MoE) has emerged as an effective approach for enhancing the capacity of deep neural network (DNN) with sub-linear computational costs. However, storing all experts on GPUs incurs significant memory overhead, increasing the monetary cost of MoE-based inference. To address this, we propose eMoE, a memory efficient inference system for MoE-based large language models (LLMs) by leveraging our observations from experiment measurements. eMoE reduces memory usage by predicting and loading only the required experts based on recurrent patterns in expert routing. To reduce loading latency while maintaining accuracy, as we found using the same experts for subsequent prompts has minimal impact on perplexity, eMoE invokes the expert predictor every few prompts rather than for each prompt. In addition, it skips predictions for tasks less sensitive to routing accuracy. Finally, it has task-aware scheduling to minimize inference latency by considering Service Level Objectives (SLOs), task-specific output lengths, and expert loading latencies. Experimental results show that compared to existing systems, eMoE reduces memory consumption by up to 80% while maintaining accuracy and reduces inference latency by up to 17%. It also enables processing prompts 40x longer, batches 4.5x larger, and achieves 1.5x higher throughput.

Emerging AI accelerators increasingly adopt wafer-scale manufacturing technologies, integrating hundreds of thousands of AI cores in a mesh architecture with large distributed on-chip memory (tens of GB in total) and ultra-high on-chip memory bandwidth (tens of PB/s). However, current LLM inference systems, optimized for shared memory architectures like GPUs, fail to exploit these accelerators fully. We introduce WaferLLM, the first wafer-scale LLM inference system. WaferLLM is guided by a novel PLMR model (pronounced as "Plummer") that captures the unique hardware characteristics of wafer-scale architectures. Leveraging this model, WaferLLM pioneers wafer-scale LLM parallelism, optimizing the utilization of hundreds of thousands of on-chip cores. It also introduces MeshGEMM and MeshGEMV, the first GEMM and GEMV implementations designed to scale effectively on wafer-scale accelerators. Evaluations show that WaferLLM achieves up to 200times higher accelerator utilization than state-of-the-art methods. Leveraging a wafer-scale accelerator (Cerebras WSE2), WaferLLM delivers GEMV operations 606times faster and 16times more energy-efficient than on an NVIDIA A100 GPU. For full LLM inference, WaferLLM achieves 10-20times speedups over A100 GPU clusters running SGLang and vLLM. These advantages are expected to grow as wafer-scale AI models, software, and hardware continue to mature. WaferLLM is open-sourced at https://github.com/MeshInfra/WaferLLM.

Web applications are increasingly becoming the primary platform for AI service delivery, making in-browser deep learning (DL) inference more prominent. However, current in-browser inference systems fail to effectively utilize advanced web programming techniques and customize kernels for various client devices, leading to suboptimal performance. To address the issues, this paper presents the first in-browser inference system, nn-JIT.web, which enables just-in-time (JIT) auto-generation of optimized kernels for both CPUs and GPUs during inference. The system achieves this by using two novel web programming techniques that can significantly reduce kernel generation time, compared to other tensor compilers such as TVM, while maintaining or even improving performance. The first technique, Tensor-Web Compiling Co-Design, lowers compiling costs by unifying tensor and web compiling and eliminating redundant and ineffective compiling passes. The second technique, Web-Specific Lite Kernel Optimization Space Design, reduces kernel tuning costs by focusing on web programming requirements and efficient hardware resource utilization, limiting the optimization space to only dozens. nn-JIT.web is evaluated for modern transformer models on a range of client devices, including the mainstream CPUs and GPUs from ARM, Intel, AMD and Nvidia. Results show that nn-JIT.web can achieve up to 8.2x faster within 30 seconds compared to the baselines across various models.

Emergency of DeepSeek R1 and QwQ 32B have broken through performance barriers for running frontier large language models (LLMs) on home devices. While consumer hardware is getting stronger and model quantization is improving, existing end-side solutions still demand GPU clusters, large RAM/VRAM, and high bandwidth, far beyond what a common home cluster can handle. This paper introduces prima.cpp, a distributed inference system that runs 70B-scale models on everyday home devices using a mix of CPU/GPU, low RAM/VRAM, Wi-Fi, and cross-platform support. It uses mmap to manage model weights and introduces piped-ring parallelism with prefetching to hide disk loading. By modeling heterogeneity in computation, communication, disk, memory (and its management behavior), and OS, it optimally assigns model layers to each device's CPU and GPU, further reducing token latency. An elegant algorithm named Halda is proposed to solve this NP-hard assignment problem. We evaluate prima.cpp on a common four-node home cluster. It outperforms llama.cpp, exo, and dllama on 30B+ models while keeping memory pressure below 6%. This brings frontier 30B-70B models, such as Llama 3, DeepSeek R1, Qwen 2.5, and QwQ to home assistants, making advanced AI truly accessible to individuals. The code is open source and available at https://github.com/Lizonghang/prima.cpp.

Advanced Large Language Models (LLMs) have achieved impressive performance across a wide range of complex and long-context natural language tasks. However, performing long-context LLM inference locally on a commodity GPU (a PC) with privacy concerns remains challenging due to the increasing memory demands of the key-value (KV) cache. Existing systems typically identify important tokens and selectively offload their KV data to GPU and CPU memory. The KV data needs to be offloaded to disk due to the limited memory on a commodity GPU, but the process is bottlenecked by token importance evaluation overhead and the disk's low bandwidth. In this paper, we present LeoAM, the first efficient importance-aware long-context LLM inference system for a single commodity GPU with adaptive hierarchical GPU-CPU-Disk KV management. Our system employs an adaptive KV management strategy that partitions KV data into variable-sized chunks based on the skewed distribution of attention weights across different layers to reduce computational and additional transmission overheads. Moreover, we propose a lightweight KV abstract method, which minimizes transmission latency by storing and extracting the KV abstract of each chunk on disk instead of the full KV data. LeoAM also leverages the dynamic compression and pipeline techniques to further accelerate inference. Experimental results demonstrate that LongInfer achieves an average inference latency speedup of 3.46x, while maintaining comparable LLM response quality. In scenarios with larger batch sizes, it achieves up to a 5.47x speedup.

Inference-time scaling can enhance the reasoning capabilities of large language models (LLMs) on complex problems that benefit from step-by-step problem solving. Although lengthening generated scratchpads has proven effective for mathematical tasks, the broader impact of this approach on other tasks remains less clear. In this work, we investigate the benefits and limitations of scaling methods across nine state-of-the-art models and eight challenging tasks, including math and STEM reasoning, calendar planning, NP-hard problems, navigation, and spatial reasoning. We compare conventional models (e.g., GPT-4o) with models fine-tuned for inference-time scaling (e.g., o1) through evaluation protocols that involve repeated model calls, either independently or sequentially with feedback. These evaluations approximate lower and upper performance bounds and potential for future performance improvements for each model, whether through enhanced training or multi-model inference systems. Our extensive empirical analysis reveals that the advantages of inference-time scaling vary across tasks and diminish as problem complexity increases. In addition, simply using more tokens does not necessarily translate to higher accuracy in these challenging regimes. Results from multiple independent runs with conventional models using perfect verifiers show that, for some tasks, these models can achieve performance close to the average performance of today's most advanced reasoning models. However, for other tasks, a significant performance gap remains, even in very high scaling regimes. Encouragingly, all models demonstrate significant gains when inference is further scaled with perfect verifiers or strong feedback, suggesting ample potential for future improvements.

Six-bit quantization (FP6) can effectively reduce the size of large language models (LLMs) and preserve the model quality consistently across varied applications. However, existing systems do not provide Tensor Core support for FP6 quantization and struggle to achieve practical performance improvements during LLM inference. It is challenging to support FP6 quantization on GPUs due to (1) unfriendly memory access of model weights with irregular bit-width and (2) high runtime overhead of weight de-quantization. To address these problems, we propose TC-FPx, the first full-stack GPU kernel design scheme with unified Tensor Core support of float-point weights for various quantization bit-width. We integrate TC-FPx kernel into an existing inference system, providing new end-to-end support (called FP6-LLM) for quantized LLM inference, where better trade-offs between inference cost and model quality are achieved. Experiments show that FP6-LLM enables the inference of LLaMA-70b using only a single GPU, achieving 1.69x-2.65x higher normalized inference throughput than the FP16 baseline. The source code will be publicly available soon.

The advent of 1-bit large language models (LLMs), led by BitNet b1.58, has spurred interest in ternary LLMs. Despite this, research and practical applications focusing on efficient edge inference for ternary LLMs remain scarce. To bridge this gap, we introduce Bitnet.cpp, an inference system optimized for BitNet b1.58 and ternary LLMs. Given that mixed-precision matrix multiplication (mpGEMM) constitutes the bulk of inference time in ternary LLMs, Bitnet.cpp incorporates a novel mpGEMM library to facilitate sub-2-bits-per-weight, efficient and lossless inference. The library features two core solutions: Ternary Lookup Table (TL), which addresses spatial inefficiencies of previous bit-wise methods, and Int2 with a Scale (I2_S), which ensures lossless edge inference, both enabling high-speed inference. Our experiments show that Bitnet.cpp achieves up to a 6.25x increase in speed over full-precision baselines and up to 2.32x over low-bit baselines, setting new benchmarks in the field. Additionally, we expand TL to element-wise lookup table (ELUT) for low-bit LLMs in the appendix, presenting both theoretical and empirical evidence of its considerable potential. Bitnet.cpp is publicly available at https://github.com/microsoft/BitNet/tree/paper , offering a sophisticated solution for the efficient and practical deployment of edge LLMs.

The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache, which imposes a huge burden on the GPU VRAM, especially for resource-constraint scenarios (e.g., edge computing and personal devices). Several cost-effective solutions leverage host memory or SSDs to reduce storage costs for offline inference scenarios and improve the throughput. Nevertheless, they suffer from significant performance penalties imposed by intensive KV cache accesses due to limited PCIe bandwidth. To address these issues, we propose InstInfer, a novel LLM inference system that offloads the most performance-critical computation (i.e., attention in decoding phase) and data (i.e., KV cache) parts to Computational Storage Drives (CSDs), which minimize the enormous KV transfer overheads. InstInfer designs a dedicated flash-aware in-storage attention engine with KV cache management mechanisms to exploit the high internal bandwidths of CSDs instead of being limited by the PCIe bandwidth. The optimized P2P transmission between GPU and CSDs further reduces data migration overheads. Experimental results demonstrate that for a 13B model using an NVIDIA A6000 GPU, InstInfer improves throughput for long-sequence inference by up to 11.1times, compared to existing SSD-based solutions such as FlexGen.

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve general LLM but fail with Low-Rank Adaptation (LoRA) inference due to three key limitations: 1) massive parameter redundancy among functions where 99% of weights are unnecessarily duplicated, 2) costly artifact loading latency beyond LLM loading, and 3) magnified resource contention when serving multiple LoRA LLMs. These inefficiencies lead to massive GPU wastage, increased Time-To-First-Token (TTFT), and high monetary costs. We propose ServerlessLoRA, a novel serverless inference system designed for faster and cheaper LoRA LLM serving. ServerlessLoRA enables secure backbone LLM sharing across isolated LoRA functions to reduce redundancy. We design a pre-loading method that pre-loads comprehensive LoRA artifacts to minimize cold-start latency. Furthermore, ServerlessLoRA employs contention aware batching and offloading to mitigate GPU resource conflicts during bursty workloads. Experiment on industrial workloads demonstrates that ServerlessLoRA reduces TTFT by up to 86% and cuts monetary costs by up to 89% compared to state-of-the-art LLM inference solutions.

The past several years have witnessed the success of transformer-based models, and their scale and application scenarios continue to grow aggressively. The current landscape of transformer models is increasingly diverse: the model size varies drastically with the largest being of hundred-billion parameters; the model characteristics differ due to the sparsity introduced by the Mixture-of-Experts; the target application scenarios can be latency-critical or throughput-oriented; the deployment hardware could be single- or multi-GPU systems with different types of memory and storage, etc. With such increasing diversity and the fast-evolving pace of transformer models, designing a highly performant and efficient inference system is extremely challenging. In this paper, we present DeepSpeed Inference, a comprehensive system solution for transformer model inference to address the above-mentioned challenges. DeepSpeed Inference consists of (1) a multi-GPU inference solution to minimize latency while maximizing the throughput of both dense and sparse transformer models when they fit in aggregate GPU memory, and (2) a heterogeneous inference solution that leverages CPU and NVMe memory in addition to the GPU memory and compute to enable high inference throughput with large models which do not fit in aggregate GPU memory. DeepSpeed Inference reduces latency by up to 7.3X over the state-of-the-art for latency-oriented scenarios and increases throughput by over 1.5x for throughput-oriented scenarios. Moreover, it enables trillion parameter scale inference under real-time latency constraints by leveraging hundreds of GPUs, an unprecedented scale for inference. It can inference 25x larger models than with GPU-only solutions, while delivering a high throughput of 84 TFLOPS (over 50% of A6000 peak).

Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model. While effective, in application-specific settings, it often involves fine-tuning both draft and target models to achieve high acceptance rates. As the number of downstream tasks grows, these draft models add significant complexity to inference systems. We propose Speculative Streaming, a single-model speculative decoding method that fuses drafting into the target model by changing the fine-tuning objective from next token prediction to future n-gram prediction. Speculative Streaming speeds up decoding by 1.8 - 3.1X in a diverse set of tasks, such as Summarization, Structured Queries, and Meaning Representation, without sacrificing generation quality. Additionally, Speculative Streaming is parameter-efficient. It achieves on-par/higher speed-ups than Medusa-style architectures while using ~10000X fewer extra parameters, making it well-suited for resource-constrained devices.

Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long contents, however, poses a challenge due to the enormous memory footprint of the transient state, known as the key-value (KV) cache, which scales with the sequence length and batch size. In this paper, we present InfiniGen, a novel KV cache management framework tailored for long-text generation, which synergistically works with modern offloading-based inference systems. InfiniGen leverages the key insight that a few important tokens that are essential for computing the subsequent attention layer in the Transformer can be speculated by performing a minimal rehearsal with the inputs of the current layer and part of the query weight and key cache of the subsequent layer. This allows us to prefetch only the essential KV cache entries (without fetching them all), thereby mitigating the fetch overhead from the host memory in offloading-based LLM serving systems. Our evaluation on several representative LLMs shows that InfiniGen improves the overall performance of a modern offloading-based system by up to 3.00x compared to prior KV cache management methods while offering substantially better model accuracy.

Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hardware-aware model-system co-design optimized for minimizing decoding costs. Step-3 innovates in two key dimensions: (1) A novel Multi-Matrix Factorization Attention (MFA) mechanism that significantly reduces both KV cache size and computation while maintaining high attention expressiveness, and (2) Attention-FFN Disaggregation (AFD), a distributed inference system that decouples attention and Feed-Forward Network (FFN) layers into specialized subsystems. This co-design achieves unprecedented cost efficiency: Step-3 significantly reduces theoretical decoding costs compared with models like DeepSeek-V3 and Qwen3 MoE 235B, with the gains widening at longer context. Step-3 achieves low cost while activating 38B parameters per token (more than DeepSeek-V3 and Qwen3 MoE 235B), demonstrating that hardware-aligned attention arithmetic intensity, MoE sparsity, and AFD are critical to cost-effectiveness. We perform a head-to-head comparison with DeepSeek-V3 in its favorable scenarios. Our implementation on Hopper GPUs achieves a decoding throughput of up to 4,039 tokens per second per GPU under 50ms TPOT SLA (4K context, FP8, no MTP). It is higher than DeepSeek-V3's 2,324 in the same setup and sets a new Pareto frontier for LLM decoding.

Retrieval-augmented generation (RAG) extends large language models (LLMs) with external data sources to enhance factual correctness and domain coverage. Modern RAG pipelines rely on large datastores, leading to system challenges in latency-sensitive deployments, especially when limited GPU memory is available. To address these challenges, we propose TeleRAG, an efficient inference system that reduces RAG latency with minimal GPU memory requirements. The core innovation of TeleRAG is lookahead retrieval, a prefetching mechanism that anticipates required data and transfers it from CPU to GPU in parallel with LLM generation. By leveraging the modularity of RAG pipelines, the inverted file index (IVF) search algorithm and similarities between queries, TeleRAG optimally overlaps data movement and computation. Experimental results show that TeleRAG reduces end-to-end RAG inference latency by up to 1.72x on average compared to state-of-the-art systems, enabling faster, more memory-efficient deployments of advanced RAG applications.

This paper describes a strategy for implementing a robotic system capable of performing General Purpose Service Robot (GPSR) tasks in robocup@home. The GPSR task is that a real robot hears a variety of commands in spoken language and executes a task in a daily life environment. To achieve the task, we integrate foundation models based inference system and a state machine task executable. The foundation models plan the task and detect objects with open vocabulary, and a state machine task executable manages each robot's actions. This system works stable, and we took first place in the RoboCup@home Japan Open 2022's GPSR with 130 points, more than 85 points ahead of the other teams.

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators. This mismatch arises from the autoregressive nature of LLMs, where the generation phase comprises operators with varying resource demands. Specifically, the attention operator is memory-intensive, exhibiting a memory access pattern that clashes with the strengths of modern accelerators, especially as context length increases. To enhance the efficiency and cost-effectiveness of LLM serving, we introduce the concept of attention offloading. This approach leverages a collection of cheap, memory-optimized devices for the attention operator while still utilizing high-end accelerators for other parts of the model. This heterogeneous setup ensures that each component is tailored to its specific workload, maximizing overall performance and cost efficiency. Our comprehensive analysis and experiments confirm the viability of splitting the attention computation over multiple devices. Also, the communication bandwidth required between heterogeneous devices proves to be manageable with prevalent networking technologies. To further validate our theory, we develop Lamina, an LLM inference system that incorporates attention offloading. Experimental results indicate that Lamina can provide 1.48x-12.1x higher estimated throughput per dollar than homogeneous solutions.

AlayaDB is a cutting-edge vector database system natively architected for efficient and effective long-context inference for Large Language Models (LLMs) at AlayaDB AI. Specifically, it decouples the KV cache and attention computation from the LLM inference systems, and encapsulates them into a novel vector database system. For the Model as a Service providers (MaaS), AlayaDB consumes fewer hardware resources and offers higher generation quality for various workloads with different kinds of Service Level Objectives (SLOs), when comparing with the existing alternative solutions (e.g., KV cache disaggregation, retrieval-based sparse attention). The crux of AlayaDB is that it abstracts the attention computation and cache management for LLM inference into a query processing procedure, and optimizes the performance via a native query optimizer. In this work, we demonstrate the effectiveness of AlayaDB via (i) three use cases from our industry partners, and (ii) extensive experimental results on LLM inference benchmarks.

Large Language Models (LLMs), despite their recent impressive accomplishments, are notably cost-prohibitive to deploy, particularly for applications involving long-content generation, such as dialogue systems and story writing. Often, a large amount of transient state information, referred to as the KV cache, is stored in GPU memory in addition to model parameters, scaling linearly with the sequence length and batch size. In this paper, we introduce a novel approach for implementing the KV cache which significantly reduces its memory footprint. Our approach is based on the noteworthy observation that a small portion of tokens contributes most of the value when computing attention scores. We call these tokens Heavy Hitters (H_2). Through a comprehensive investigation, we find that (i) the emergence of H_2 is natural and strongly correlates with the frequent co-occurrence of tokens in the text, and (ii) removing them results in significant performance degradation. Based on these insights, we propose Heavy Hitter Oracle (H_2O), a KV cache eviction policy that dynamically retains a balance of recent and H_2 tokens. We formulate the KV cache eviction as a dynamic submodular problem and prove (under mild assumptions) a theoretical guarantee for our novel eviction algorithm which could help guide future work. We validate the accuracy of our algorithm with OPT, LLaMA, and GPT-NeoX across a wide range of tasks. Our implementation of H_2O with 20% heavy hitters improves the throughput over three leading inference systems DeepSpeed Zero-Inference, Hugging Face Accelerate, and FlexGen by up to 29times, 29times, and 3times on OPT-6.7B and OPT-30B. With the same batch size, H2O can reduce the latency by up to 1.9times. The code is available at https://github.com/FMInference/H2O.

As the training of giant dense models hits the boundary on the availability and capability of the hardware resources today, Mixture-of-Experts (MoE) models become one of the most promising model architectures due to their significant training cost reduction compared to a quality-equivalent dense model. Its training cost saving is demonstrated from encoder-decoder models (prior works) to a 5x saving for auto-aggressive language models (this work along with parallel explorations). However, due to the much larger model size and unique architecture, how to provide fast MoE model inference remains challenging and unsolved, limiting its practical usage. To tackle this, we present DeepSpeed-MoE, an end-to-end MoE training and inference solution as part of the DeepSpeed library, including novel MoE architecture designs and model compression techniques that reduce MoE model size by up to 3.7x, and a highly optimized inference system that provides 7.3x better latency and cost compared to existing MoE inference solutions. DeepSpeed-MoE offers an unprecedented scale and efficiency to serve massive MoE models with up to 4.5x faster and 9x cheaper inference compared to quality-equivalent dense models. We hope our innovations and systems help open a promising path to new directions in the large model landscape, a shift from dense to sparse MoE models, where training and deploying higher-quality models with fewer resources becomes more widely possible.

This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems. Specifically, in terms of model architecture, we propose InfLLM v2, a trainable sparse attention mechanism that accelerates both prefilling and decoding phases for long-context processing. Regarding training data, we propose UltraClean, an efficient and accurate pre-training data filtering and generation strategy, and UltraChat v2, a comprehensive supervised fine-tuning dataset. These datasets enable satisfactory model performance to be achieved using just 8 trillion training tokens. Regarding training algorithms, we propose ModelTunnel v2 for efficient pre-training strategy search, and improve existing post-training methods by introducing chunk-wise rollout for load-balanced reinforcement learning and data-efficient tenary LLM, BitCPM. Regarding inference systems, we propose CPM.cu that integrates sparse attention, model quantization, and speculative sampling to achieve efficient prefilling and decoding. To meet diverse on-device requirements, MiniCPM4 is available in two versions, with 0.5B and 8B parameters, respectively. Sufficient evaluation results show that MiniCPM4 outperforms open-source models of similar size across multiple benchmarks, highlighting both its efficiency and effectiveness. Notably, MiniCPM4-8B demonstrates significant speed improvements over Qwen3-8B when processing long sequences. Through further adaptation, MiniCPM4 successfully powers diverse applications, including trustworthy survey generation and tool use with model context protocol, clearly showcasing its broad usability.

Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data. However, edge devices often struggle with limited computing power, memory, and bandwidth, requiring collaboration across multiple devices to run and speed up LLM inference. Pipeline parallelism, the mainstream solution, is inefficient for single-user scenarios, while tensor parallelism struggles with frequent communications. In this paper, we argue that tensor parallelism can be more effective than pipeline on low-resource devices, and present a compute- and memory-efficient tensor parallel inference system, named TPI-LLM, to serve 70B-scale models. TPI-LLM keeps sensitive raw data local in the users' devices and introduces a sliding window memory scheduler to dynamically manage layer weights during inference, with disk I/O latency overlapped with the computation and communication. This allows larger models to run smoothly on memory-limited devices. We analyze the communication bottleneck and find that link latency, not bandwidth, emerges as the main issue, so a star-based allreduce algorithm is implemented. Through extensive experiments on both emulated and real testbeds, TPI-LLM demonstrated over 80% less time-to-first-token and token latency compared to Accelerate, and over 90% compared to Transformers and Galaxy, while cutting the peak memory footprint of Llama 2-70B by 90%, requiring only 3.1 GB of memory for 70B-scale models.

Mixture of Experts (MoE) LLMs, characterized by their sparse activation patterns, offer a promising approach to scaling language models while avoiding proportionally increasing the inference cost. However, their large parameter sizes present deployment challenges in resource-constrained environments with limited GPU memory capacity, as GPU memory is often insufficient to accommodate the full set of model weights. Consequently, typical deployments rely on CPU-GPU hybrid execution: the GPU handles compute-intensive GEMM operations, while the CPU processes the relatively lightweight attention mechanism. This setup introduces a key challenge: how to effectively optimize resource utilization across CPU and GPU? Prior work has designed system optimizations based on performance models with limited scope. Specifically, such models do not capture the complex interactions between hardware properties and system execution mechanisms. Therefore, previous approaches neither identify nor achieve the hardware limit. This paper presents MoE-Lens, a high-throughput MoE LLM inference system designed through holistic performance modeling for resource-constrained environments. Our performance model thoroughly analyzes various fundamental system components, including CPU memory capacity, GPU compute power, and workload characteristics, to understand the theoretical performance upper bound of MoE inference. Furthermore, it captures the system execution mechanisms to identify the key hardware bottlenecks and accurately predict the achievable throughput. Informed by our performance model, MoE-Lens introduces an inference system approaching hardware limits. Evaluated on diverse MoE models and datasets, MoE-Lens outperforms the state-of-the-art solution by 4.6x on average (up to 25.5x), with our theoretical model predicting performance with an average 94% accuracy.

Semantic top-K selection with cross-encoder rerankers underpins of on-device AI services, such as retrieval-augmented generation, agent memory, and personalized recommendation. However, its latency and memory demands dominate end-to-end budgets on edge hardware. Revisiting the objective of top-K selection, we reveal that only relative rankings matter, not exact per-candidate scores. We further observe sequence-level sparsity: relative rankings stabilize early in intermediate layers, allowing pruning opportunities prior to completing full inference. Building on this insight, we propose monolithic forwarding and develop a training-free inference system, GRATING. By maintaining a global view of all candidates, it reduces latency through progressive cluster pruning. It also bounds peak memory usage by strategically overlapping I/O with computation via dual-layer sliding window and chunked execution. We evaluate GRATING against state-of-the-art baselines on rerankers from 0.6B to 8B parameters across Apple M2 and RTX 5070. GRATING consistently reduces latency by up to 89.0% and peak memory by up to 94.9% in microbenchmarks, without any loss in precision. Across three real-world on-device AI applications, GRATING lowers latency by 11.6%-51.0% and peak memory by 18.6%-77.8%, demonstrating substantial improvements in efficiency and deployability.

The rapid advancement of Large Language Models (LLMs) has established language as a core general-purpose cognitive substrate, driving the demand for specialized Language Processing Units (LPUs) tailored for LLM inference. To overcome the growing energy consumption of LLM inference systems, this paper proposes a Hardwired-Neurons Language Processing Unit (HNLPU), which physically hardwires LLM weight parameters into the computational fabric, achieving several orders of magnitude computational efficiency improvement by extreme specialization. However, a significant challenge still lies in the scale of modern LLMs. An ideal estimation on hardwiring gpt-oss 120 B requires fabricating at least 6 billion dollars of photomask sets, rendering the straightforward solution economically impractical. Addressing this challenge, we propose the novel Metal-Embedding methodology. Instead of embedding weights in a 2D grid of silicon device cells, Metal-Embedding embeds weight parameters into the 3D topology of metal wires. This brings two benefits: (1) a 15x increase in density, and (2) 60 out of 70 layers of photomasks are made homogeneous across chips, including all EUV photomasks. In total, Metal-Embedding reduced the photomask cost by 112x, bringing the Non-Recurring Engineering (NRE) cost of HNLPU into an economically viable range. Experimental results show that HNLPU achieved 249,960 tokens/s (5,555x/85x of GPU/WSE), 36 tokens/J (1,047x/283x of GPU/WSE), 13,232 mm2 total die area (29% inscribed rectangular area in a 300 mm wafer), \$184M estimated NRE at 5 nm technology. Analysis shows that HNLPU achieved 8.57x cost-effectiveness and 230x carbon footprint reduction compared to H100 clusters, under an annual weight updating assumption.

Real-time Automatic Speech Recognition (ASR) is a fundamental building block for many commercial applications of ML, including live captioning, dictation, meeting transcriptions, and medical scribes. Accuracy and latency are the most important factors when companies select a system to deploy. We present WhisperKit, an optimized on-device inference system for real-time ASR that significantly outperforms leading cloud-based systems. We benchmark against server-side systems that deploy a diverse set of models, including a frontier model (OpenAI gpt-4o-transcribe), a proprietary model (Deepgram nova-3), and an open-source model (Fireworks large-v3-turbo).Our results show that WhisperKit matches the lowest latency at 0.46s while achieving the highest accuracy 2.2% WER. The optimizations behind the WhisperKit system are described in detail in this paper.

Our hands serve as a fundamental means of interaction with the world around us. Therefore, understanding hand poses and interaction context is critical for human-computer interaction. We present EchoWrist, a low-power wristband that continuously estimates 3D hand pose and recognizes hand-object interactions using active acoustic sensing. EchoWrist is equipped with two speakers emitting inaudible sound waves toward the hand. These sound waves interact with the hand and its surroundings through reflections and diffractions, carrying rich information about the hand's shape and the objects it interacts with. The information captured by the two microphones goes through a deep learning inference system that recovers hand poses and identifies various everyday hand activities. Results from the two 12-participant user studies show that EchoWrist is effective and efficient at tracking 3D hand poses and recognizing hand-object interactions. Operating at 57.9mW, EchoWrist is able to continuously reconstruct 20 3D hand joints with MJEDE of 4.81mm and recognize 12 naturalistic hand-object interactions with 97.6% accuracy.

The KV-Cache technique has become the standard for the inference of large language models (LLMs). It caches states of self-attention to avoid recomputation. Yet, it is widely criticized that KV-Cache can become a bottleneck of the LLM inference system, especially when confronted with ultra-large models and long-context queries. A natural remedy is to discard the KV-Cache for less important tokens, with StreamingLLM as an example, but the used static eviction strategies cannot flexibly adapt to varying contexts. Remedies like H2O leverage accumulative attention scores to perform dynamic eviction but suffer from the attention bias issue in capturing contextual information. This paper bridges this gap by devising a parameterized KV-Cache eviction mechanism, dubbed as Attention-Gate, which accepts the whole context as input and yields eviction flags for each token to realize in-context eviction. The subsequent self-attention module proceeds according to the flags and only the KV states for the remaining tokens need to be cached. The Attention-Gates can vary among different heads and layers and be trivially plugged into pre-trained LLMs, tuned by cost-effective continual pre-training or supervised fine-tuning objectives to acquire what to discard. The computational and memory overhead introduced by Attention-Gates is minimal. Our method is validated across multiple tasks, demonstrating both efficiency and adaptability. After a highly efficient continual pre-training, it achieves higher average accuracy and evicts more tokens compared to traditional training-free methods. In supervised fine-tuning, it not only evicts many tokens but also outperforms LoRA-finetuned LLMs on some datasets, such as RTE, where it improves accuracy by 13.9% while evicting 62.8% of tokens, showing that effective eviction of redundant tokens can even enhance performance.

Retrieval-Augmented Generation (RAG) has shown significant improvements in various natural language processing tasks by integrating the strengths of large language models (LLMs) and external knowledge databases. However, RAG introduces long sequence generation and leads to high computation and memory costs. We propose RAGCache, a novel multilevel dynamic caching system tailored for RAG. Our analysis benchmarks current RAG systems, pinpointing the performance bottleneck (i.e., long sequence due to knowledge injection) and optimization opportunities (i.e., caching knowledge's intermediate states). Based on these insights, we design RAGCache, which organizes the intermediate states of retrieved knowledge in a knowledge tree and caches them in the GPU and host memory hierarchy. RAGCache proposes a replacement policy that is aware of LLM inference characteristics and RAG retrieval patterns. It also dynamically overlaps the retrieval and inference steps to minimize the end-to-end latency. We implement RAGCache and evaluate it on vLLM, a state-of-the-art LLM inference system and Faiss, a state-of-the-art vector database. The experimental results show that RAGCache reduces the time to first token (TTFT) by up to 4x and improves the throughput by up to 2.1x compared to vLLM integrated with Faiss.

Current Retrieval-Augmented Generation (RAG) systems concatenate and process numerous retrieved document chunks for prefill which requires a large volume of computation, therefore leading to significant latency in time-to-first-token (TTFT). To reduce the computation overhead as well as TTFT, we introduce TurboRAG, a novel RAG system that redesigns the inference paradigm of the current RAG system by first pre-computing and storing the key-value (KV) caches of documents offline, and then directly retrieving the saved KV cache for prefill. Hence, online computation of KV caches is eliminated during inference. In addition, we provide a number of insights into the mask matrix and positional embedding mechanisms, plus fine-tune a pretrained language model to maintain model accuracy of TurboRAG. Our approach is applicable to most existing large language models and their applications without any requirement in modification of models and inference systems. Experimental results across a suite of RAG benchmarks demonstrate that TurboRAG reduces TTFT by up to 9.4x compared to the conventional RAG systems (on an average of 8.6x), but reserving comparable performance to the standard RAG systems.

Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that evolves programs to improve bounds on open problems. However, it relies on ensembles of frontier LLMs to achieve new bounds and is a pure inference system that models cannot internalize the evolving strategies. We introduce ThetaEvolve, an open-source framework that simplifies and extends AlphaEvolve to efficiently scale both in-context learning and Reinforcement Learning (RL) at test time, allowing models to continually learn from their experiences in improving open optimization problems. ThetaEvolve features a single LLM, a large program database for enhanced exploration, batch sampling for higher throughput, lazy penalties to discourage stagnant outputs, and optional reward shaping for stable training signals, etc. ThetaEvolve is the first evolving framework that enable a small open-source model, like DeepSeek-R1-0528-Qwen3-8B, to achieve new best-known bounds on open problems (circle packing and first auto-correlation inequality) mentioned in AlphaEvolve. Besides, across two models and four open tasks, we find that ThetaEvolve with RL at test-time consistently outperforms inference-only baselines, and the model indeed learns evolving capabilities, as the RL-trained checkpoints demonstrate faster progress and better final performance on both trained target task and other unseen tasks. We release our code publicly: https://github.com/ypwang61/ThetaEvolve

Current Multimodal Large Language Models (MLLMs) may struggle with understanding long or complex videos due to computational demands at test time, lack of robustness, and limited accuracy, primarily stemming from their feed-forward processing nature. These limitations could be more severe for models with fewer parameters. To address these limitations, we propose a novel framework inspired by cybernetic principles, redesigning video MLLMs as adaptive systems capable of self-monitoring, self-correction, and dynamic resource allocation during inference. Our approach, CyberV, introduces a cybernetic loop consisting of an MLLM Inference System, a Sensor, and a Controller. Specifically, the sensor monitors forward processes of the MLLM and collects intermediate interpretations, such as attention drift, then the controller determines when and how to trigger self-correction and generate feedback to guide the next round. This test-time adaptive scaling framework enhances frozen MLLMs without requiring retraining or additional components. Experiments demonstrate significant improvements: CyberV boosts Qwen2.5-VL-7B by 8.3% and InternVL3-8B by 5.5% on VideoMMMU, surpassing the competitive proprietary model GPT-4o. When applied to Qwen2.5-VL-72B, it yields a 10.0% improvement, achieving performance even comparable to human experts. Furthermore, our method demonstrates consistent gains on general-purpose benchmarks, such as VideoMME and WorldSense, highlighting its effectiveness and generalization capabilities in making MLLMs more robust and accurate for dynamic video understanding. The code is released at https://github.com/marinero4972/CyberV.

The emerging field of Vision-Language-Action (VLA) for humanoid robots faces several fundamental challenges, including the high cost of data acquisition, the lack of a standardized benchmark, and the significant gap between simulation and the real world. To overcome these obstacles, we propose RealMirror, a comprehensive, open-source embodied AI VLA platform. RealMirror builds an efficient, low-cost data collection, model training, and inference system that enables end-to-end VLA research without requiring a real robot. To facilitate model evolution and fair comparison, we also introduce a dedicated VLA benchmark for humanoid robots, featuring multiple scenarios, extensive trajectories, and various VLA models. Furthermore, by integrating generative models and 3D Gaussian Splatting to reconstruct realistic environments and robot models, we successfully demonstrate zero-shot Sim2Real transfer, where models trained exclusively on simulation data can perform tasks on a real robot seamlessly, without any fine-tuning. In conclusion, with the unification of these critical components, RealMirror provides a robust framework that significantly accelerates the development of VLA models for humanoid robots. Project page: https://terminators2025.github.io/RealMirror.github.io

On-device large language models (LLMs) are catalyzing novel mobile applications such as UI task automation and personalized email auto-reply, without giving away users' private data. However, on-device LLMs still suffer from unacceptably long inference latency, especially the time to first token (prefill stage) due to the need of long context for accurate, personalized content generation, as well as the lack of parallel computing capacity of mobile CPU/GPU. To enable practical on-device LLM, we present mllm-NPU, the first-of-its-kind LLM inference system that efficiently leverages on-device Neural Processing Unit (NPU) offloading. Essentially, mllm-NPU is an algorithm-system co-design that tackles a few semantic gaps between the LLM architecture and contemporary NPU design. Specifically, it re-constructs the prompt and model in three levels: (1) At prompt level, it divides variable-length prompts into multiple fixed-sized chunks while maintaining data dependencies; (2) At tensor level, it identifies and extracts significant outliers to run on the CPU/GPU in parallel with minimal overhead; (3) At block level, it schedules Transformer blocks in an out-of-order manner to the CPU/GPU and NPU based on their hardware affinity and sensitivity to accuracy. Compared to competitive baselines, mllm-NPU achieves 22.4x faster prefill speed and 30.7x energy savings on average, and up to 32.8x speedup in an end-to-end real-world application. For the first time, mllm-NPU achieves more than 1,000 tokens/sec prefilling for a billion-sized model (Qwen1.5-1.8B), paving the way towards practical on-device LLM.

Transformer models pre-trained with a masked-language-modeling objective (e.g., BERT) encode commonsense knowledge as evidenced by behavioral probes; however, the extent to which this knowledge is acquired by systematic inference over the semantics of the pre-training corpora is an open question. To answer this question, we selectively inject verbalized knowledge into the minibatches of a BERT model during pre-training and evaluate how well the model generalizes to supported inferences. We find generalization does not improve over the course of pre-training, suggesting that commonsense knowledge is acquired from surface-level, co-occurrence patterns rather than induced, systematic reasoning.

Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, existing large language models face increasing computational and memory challenges, which hinder their ability to provide efficient and responsive interactions. Most current acceleration methods either compress the context or optimize key value caching, but they often rely on fixed or position-based heuristics that do not adapt well to the dynamic and unpredictable patterns found in actual multi-turn conversations. In this paper, we present LoopServe, an adaptive dual-phase inference acceleration framework for large language models in multi-turn dialogues. LoopServe introduces two main innovations. First, it performs online sparsification during the prefilling phase by dynamically selecting the most important parts of the attention matrix for each new input. Second, it uses progressive key value compression during decoding by adaptively maintaining a relevant and efficient cache based on the most recently generated output tokens. We also propose a https://huggingface.co/datasets/TreeAILab/Multi-turn_Long-context_Benchmark_for_LLMs{new benchmark} with eleven multi-turn datasets that reflect realistic query positions and conversational dependencies. Extensive experiments demonstrate that LoopServe consistently achieves superior effectiveness compared to existing baselines and significantly accelerates LLM inference across a wide range of long-context dialogue tasks.

While Bayesian inference provides a principled framework for reasoning under uncertainty, its widespread adoption is limited by the intractability of exact posterior computation, necessitating the use of approximate inference. However, existing methods are often computationally expensive, or demand costly retraining when priors change, limiting their utility, particularly in sequential inference problems such as real-time sensor fusion. To address these challenges, we introduce the Distribution Transformer -- a novel architecture that can learn arbitrary distribution-to-distribution mappings. Our method can be trained to map a prior to the corresponding posterior, conditioned on some dataset -- thus performing approximate Bayesian inference. Our novel architecture represents a prior distribution as a (universally-approximating) Gaussian Mixture Model (GMM), and transforms it into a GMM representation of the posterior. The components of the GMM attend to each other via self-attention, and to the datapoints via cross-attention. We demonstrate that Distribution Transformers both maintain flexibility to vary the prior, and significantly reduces computation times-from minutes to milliseconds-while achieving log-likelihood performance on par with or superior to existing approximate inference methods across tasks such as sequential inference, quantum system parameter inference, and Gaussian Process predictive posterior inference with hyperpriors.

Effective control and prediction of dynamical systems often require appropriate handling of continuous-time and discrete, event-triggered processes. Stochastic hybrid systems (SHSs), common across engineering domains, provide a formalism for dynamical systems subject to discrete, possibly stochastic, state jumps and multi-modal continuous-time flows. Despite the versatility and importance of SHSs across applications, a general procedure for the explicit learning of both discrete events and multi-mode continuous dynamics remains an open problem. This work introduces Neural Hybrid Automata (NHAs), a recipe for learning SHS dynamics without a priori knowledge on the number of modes and inter-modal transition dynamics. NHAs provide a systematic inference method based on normalizing flows, neural differential equations and self-supervision. We showcase NHAs on several tasks, including mode recovery and flow learning in systems with stochastic transitions, and end-to-end learning of hierarchical robot controllers.

Being able to provide explanations for a model's decision has become a central requirement for the development, deployment, and adoption of machine learning models. However, we are yet to understand what explanation methods can and cannot do. How do upstream factors such as data, model prediction, hyperparameters, and random initialization influence downstream explanations? While previous work raised concerns that explanations (E) may have little relationship with the prediction (Y), there is a lack of conclusive study to quantify this relationship. Our work borrows tools from causal inference to systematically assay this relationship. More specifically, we study the relationship between E and Y by measuring the treatment effect when intervening on their causal ancestors, i.e., on hyperparameters and inputs used to generate saliency-based Es or Ys. Our results suggest that the relationships between E and Y is far from ideal. In fact, the gap between 'ideal' case only increase in higher-performing models -- models that are likely to be deployed. Our work is a promising first step towards providing a quantitative measure of the relationship between E and Y, which could also inform the future development of methods for E with a quantitative metric.

We present that hierarchical LLM reasoning via scaling thought templates can effectively optimize the reasoning search space and outperform the mathematical reasoning capabilities of powerful LLMs like OpenAI o1-preview and DeepSeek V3. We train our ReasonFlux-32B model with only 8 GPUs and introduces three innovations: (i) a structured and generic thought template library, containing around 500 high-level thought templates capable of generalizing to similar or relevant reasoning problems; (ii) performing hierarchical reinforcement learning on a sequence of thought templates instead of long CoTs, optimizing a base LLM to plan out an optimal template trajectory for gradually handling complex problems; (iii) a brand new inference scaling system that enables hierarchical LLM reasoning by adaptively scaling thought templates at inference time. With a template trajectory containing sequential thought templates, our ReasonFlux-32B significantly advances math reasoning capabilities to state-of-the-art levels. Notably, on the MATH benchmark, it achieves an accuracy of 91.2% and surpasses o1-preview by 6.7%. On the USA Math Olympiad (AIME) benchmark, ReasonFlux-32B solves an average of 56.7% of problems, surpassing o1-preview and DeepSeek-V3 by 27% and 45%, respectively. Code: https://github.com/Gen-Verse/ReasonFlux

Complex, temporally evolving phenomena, from climate to brain activity, are governed by dynamical systems (DS). DS reconstruction (DSR) seeks to infer generative surrogate models of these from observed data, reproducing their long-term behavior. Existing DSR approaches require purpose-training for any new system observed, lacking the zero-shot and in-context inference capabilities known from LLMs. Here we introduce DynaMix, a novel multivariate ALRNN-based mixture-of-experts architecture pre-trained for DSR, the first DSR model able to generalize zero-shot to out-of-domain DS. Just from a provided context signal, without any re-training, DynaMix faithfully forecasts the long-term evolution of novel DS where existing time series (TS) foundation models, like Chronos, fail -- at a fraction of the number of parameters and orders of magnitude faster inference times. DynaMix outperforms TS foundation models in terms of long-term statistics, and often also short-term forecasts, even on real-world time series, like traffic or weather data, typically used for training and evaluating TS models, but not at all part of DynaMix' training corpus. We illustrate some of the failure modes of TS models for DSR problems, and conclude that models built on DS principles may bear a huge potential also for advancing the TS prediction field.

Modern Large Language Model (LLM) systems typically rely on Retrieval Augmented Generation (RAG) which aims to gather context that is useful for response generation. These RAG systems typically optimize strictly towards retrieving context that is maximally relevant to the query. However, conventional theory suggests that retrieval systems which seek to maximize context relevance without any additional explicit criteria can create information bottlenecks. We reaffirm this finding in the modern age of LLM's by showing that in standard RAG pipelines, maximizing for context relevance alone can degrade downstream response quality. In response, we show evaluations of existing RAG methods which account for both context relevance and answer quality. These evaluations introduce a novel finding that existing RAG systems scale poorly with inference time compute usage when considering our combined metric. We introduce "RErank BEyond reLevance (REBEL)", which enables RAG systems to scale with inference-time compute via injection of multi-criteria optimization using Chain-of-Thought prompting (and optionally Multi-Turn dialogue). Ultimately, this enables a new performance/speed tradeoff curve, where RAG systems are able to achieve both higher relevance of retrieved contexts and superior answer quality as inference time increases. Code for the implementation of our method in llama-index can be found at the following PR: https://github.com/run-llama/llama_index/pull/17590. Code for running experiments using this llama-index implementation can be found at https://github.com/microsoft/REBEL.

The deployment of large-scale models, such as large language models (LLMs) and sophisticated image generation systems, incurs substantial costs due to their computational demands. To mitigate these costs and address challenges related to scalability and data security, there is a growing shift towards decentralized systems for deploying such models. In these decentralized environments, efficient inference acceleration becomes crucial to manage computational resources effectively and enhance system responsiveness. In this work, we address the challenge of selecting optimal acceleration methods in decentralized systems by introducing a meta-learning-based framework. This framework automates the selection process by learning from historical performance data of various acceleration techniques across different tasks. Unlike traditional methods that rely on random selection or expert intuition, our approach systematically identifies the best acceleration strategies based on the specific characteristics of each task. We demonstrate that our meta-learning framework not only streamlines the decision-making process but also consistently outperforms conventional methods in terms of efficiency and performance. Our results highlight the potential of meta-learning to revolutionize inference acceleration in decentralized AI systems, offering a path towards more democratic and economically feasible artificial intelligence solutions.

Large language models (LLMs) can spend extra compute during inference to generate intermediate thoughts, which helps to produce better final responses. Since Chain-of-Thought (Wei et al., 2022), many such System 2 techniques have been proposed such as Rephrase and Respond (Deng et al., 2023a), System 2 Attention (Weston and Sukhbaatar, 2023) and Branch-Solve-Merge (Saha et al., 2023). In this work we investigate self-supervised methods to ``compile'' (distill) higher quality outputs from System 2 techniques back into LLM generations without intermediate reasoning token sequences, as this reasoning has been distilled into System 1. We show that several such techniques can be successfully distilled, resulting in improved results compared to the original System 1 performance, and with less inference cost than System 2. We posit that such System 2 distillation will be an important feature of future continually learning AI systems, enabling them to focus System 2 capabilities on the reasoning tasks that they cannot yet do well.

Many NLP tasks benefit from using large language models (LLMs) that often have more than 100 billion parameters. With the release of BLOOM-176B and OPT-175B, everyone can download pretrained models of this scale. Still, using these models requires high-end hardware unavailable to many researchers. In some cases, LLMs can be used more affordably via RAM offloading or hosted APIs. However, these techniques have innate limitations: offloading is too slow for interactive inference, while APIs are not flexible enough for research that requires access to weights, attention or logits. In this work, we propose Petals - a system for inference and fine-tuning of large models collaboratively by joining the resources of multiple parties. We demonstrate that this strategy outperforms offloading for very large models, running inference of BLOOM-176B on consumer GPUs with approx 1 step per second, which is enough for many interactive LLM applications. Unlike most inference APIs, Petals also natively exposes hidden states of served models, allowing to train and share custom model extensions based on efficient fine-tuning methods.

Large language models (LLMs) have demonstrated significant success in complex reasoning tasks such as math and coding. In contrast to these tasks where deductive reasoning predominates, inductive reasoning-the ability to derive general rules from incomplete evidence, remains underexplored. This paper investigates extended inductive reasoning in LLMs through the lens of personalized preference inference, a critical challenge in LLM alignment where current approaches struggle to capture diverse user preferences. The task demands strong inductive reasoning capabilities as user preferences are typically embedded implicitly across various interaction forms, requiring models to synthesize consistent preference patterns from scattered signals. We propose AlignXplore, a model that leverages extended reasoning chains to enable systematic preference inference from behavioral signals in users' interaction histories. Such explicit preference articulation enables efficient streaming inference: when new behavioral signals emerge, the model can directly build upon previously inferred preference descriptions rather than reprocessing historical signals from scratch, while also supporting iterative refinement to the inferred preferences. We develop AlignXplore by combining cold-start training based on synthetic data with subsequent online reinforcement learning. Through extensive experiments, we demonstrate that AlignXplore achieves substantial improvements over the backbone model by an average of 15.49\% on in-domain and out-of-domain benchmarks, while maintaining strong generalization ability across different input formats and downstream models. Further analyses establish best practices for preference inference learning through systematic comparison of reward modeling strategies, while revealing the emergence of human-like inductive reasoning patterns during training.

Modern large language models (LLMs) employ various forms of logical inference, both implicitly and explicitly, when addressing reasoning tasks. Understanding how to optimally leverage these inference paradigms is critical for advancing LLMs' reasoning capabilities. This paper adopts an exploratory approach by introducing a controlled evaluation environment for analogical reasoning -- a fundamental cognitive task -- that is systematically parameterized across three dimensions: modality (textual, visual, symbolic), difficulty (easy, medium, hard), and task format (multiple-choice or free-text generation). We analyze the comparative dynamics of inductive, abductive, and deductive inference pipelines across these dimensions, and demonstrate that our findings generalize to broader in-context learning tasks. Additionally, we investigate advanced paradigms such as hypothesis selection, verification, and refinement, revealing their potential to scale up logical inference in LLM reasoning. This exploratory study provides a foundation for future research in enhancing LLM reasoning through systematic logical inference strategies.

In large language models like the Generative Pre-trained Transformer, the Mixture of Experts paradigm has emerged as a powerful technique for enhancing model expressiveness and accuracy. However, deploying GPT MoE models for parallel inference on distributed systems presents significant challenges, primarily due to the extensive Alltoall communication required for expert routing and aggregation. This communication bottleneck exacerbates the already complex computational landscape, hindering the efficient utilization of high-performance computing resources. In this paper, we propose a lightweight optimization technique called ExFlow, to largely accelerate the inference of these MoE models. We take a new perspective on alleviating the communication overhead by exploiting the inter-layer expert affinity. Unlike previous methods, our solution can be directly applied to pre-trained MoE models without any fine-tuning or accuracy degradation. By proposing a context-coherent expert parallelism on distributed systems, our design only uses one Alltoall communication to deliver the same functionality while previous methods all require two Alltoalls. By carefully examining the conditional probability in tokens' routing across multiple layers, we proved that pre-trained GPT MoE models implicitly exhibit a strong inter-layer expert affinity. We then design an efficient integer programming model to capture such features and show that by properly placing the experts on corresponding GPUs, we can reduce up to 67% cross-GPU routing latency. Our solution beats the cutting-edge MoE implementations with experts from 8 to 64, with up to 2.2x improvement in inference throughput. We further provide a detailed study of how the model implicitly acquires this expert affinity at the very early training stage and how this affinity evolves and stabilizes during training.

Large Language Models (LLMs) hold immense potential to generate synthetic data of high quality and utility, which has numerous applications from downstream model training to practical data utilisation. However, contemporary models, despite their impressive capacities, consistently struggle to produce both coherent and diverse data. To address the coherency issue, we introduce contrastive expert guidance, where the difference between the logit distributions of fine-tuned and base language models is emphasised to ensure domain adherence. In order to ensure diversity, we utilise existing real and synthetic examples as negative prompts to the model. We deem this dual-pronged approach to logit reshaping as STEER: Semantic Text Enhancement via Embedding Repositioning. STEER operates at inference-time and systematically guides the LLMs to strike a balance between adherence to the data distribution (ensuring semantic fidelity) and deviation from prior synthetic examples or existing real datasets (ensuring diversity and authenticity). This delicate balancing act is achieved by dynamically moving towards or away from chosen representations in the latent space. STEER demonstrates improved performance over previous synthetic data generation techniques, exhibiting better balance between data diversity and coherency across three distinct tasks: hypothesis generation, toxic and non-toxic comment generation, and commonsense reasoning task generation. We demonstrate how STEER allows for fine-tuned control over the diversity-coherency trade-off via its hyperparameters, highlighting its versatility.

Interactive storytelling benefits from planning and exploring multiple 'what if' scenarios. Modern LLMs are useful tools for ideation and exploration, but current chat-based user interfaces restrict users to a single linear flow. To address this limitation, we propose Narrative Studio -- a novel in-browser narrative exploration environment featuring a tree-like interface that allows branching exploration from user-defined points in a story. Each branch is extended via iterative LLM inference guided by system and user-defined prompts. Additionally, we employ Monte Carlo Tree Search (MCTS) to automatically expand promising narrative paths based on user-specified criteria, enabling more diverse and robust story development. We also allow users to enhance narrative coherence by grounding the generated text in an entity graph that represents the actors and environment of the story.

Pretrained time series models have enabled inference-only forecasting systems that produce accurate predictions without task-specific training. However, existing approaches largely focus on univariate forecasting, limiting their applicability in real-world scenarios where multivariate data and covariates play a crucial role. We present Chronos-2, a pretrained model capable of handling univariate, multivariate, and covariate-informed forecasting tasks in a zero-shot manner. Chronos-2 employs a group attention mechanism that facilitates in-context learning (ICL) through efficient information sharing across multiple time series within a group, which may represent sets of related series, variates of a multivariate series, or targets and covariates in a forecasting task. These general capabilities are achieved through training on synthetic datasets that impose diverse multivariate structures on univariate series. Chronos-2 delivers state-of-the-art performance across three comprehensive benchmarks: fev-bench, GIFT-Eval, and Chronos Benchmark II. On fev-bench, which emphasizes multivariate and covariate-informed forecasting, Chronos-2's universal ICL capabilities lead to substantial improvements over existing models. On tasks involving covariates, it consistently outperforms baselines by a wide margin. Case studies in the energy and retail domains further highlight its practical advantages. The in-context learning capabilities of Chronos-2 establish it as a general-purpose forecasting model that can be used "as is" in real-world forecasting pipelines.

Synthetic data generation has become essential for securely sharing and analyzing sensitive data sets. Traditional anonymization techniques, however, often fail to adequately preserve privacy. We introduce the Tabular Auto-Regressive Generative Network (TabularARGN), a neural network architecture specifically designed for generating high-quality synthetic tabular data. Using a discretization-based auto-regressive approach, TabularARGN achieves high data fidelity while remaining computationally efficient. We evaluate TabularARGN against existing synthetic data generation methods, showing competitive results in statistical similarity, machine learning utility, and detection robustness. We further perform an in-depth privacy evaluation using systematic membership-inference attacks, highlighting the robustness and effective privacy-utility balance of our approach.

We introduce the concept of "universal password model" -- a password model that, once pre-trained, can automatically adapt its guessing strategy based on the target system. To achieve this, the model does not need to access any plaintext passwords from the target credentials. Instead, it exploits users' auxiliary information, such as email addresses, as a proxy signal to predict the underlying password distribution. Specifically, the model uses deep learning to capture the correlation between the auxiliary data of a group of users (e.g., users of a web application) and their passwords. It then exploits those patterns to create a tailored password model for the target system at inference time. No further training steps, targeted data collection, or prior knowledge of the community's password distribution is required. Besides improving over current password strength estimation techniques and attacks, the model enables any end-user (e.g., system administrators) to autonomously generate tailored password models for their systems without the often unworkable requirements of collecting suitable training data and fitting the underlying machine learning model. Ultimately, our framework enables the democratization of well-calibrated password models to the community, addressing a major challenge in the deployment of password security solutions at scale.

Simulation-based inference with conditional neural density estimators is a powerful approach to solving inverse problems in science. However, these methods typically treat the underlying forward model as a black box, with no way to exploit geometric properties such as equivariances. Equivariances are common in scientific models, however integrating them directly into expressive inference networks (such as normalizing flows) is not straightforward. We here describe an alternative method to incorporate equivariances under joint transformations of parameters and data. Our method -- called group equivariant neural posterior estimation (GNPE) -- is based on self-consistently standardizing the "pose" of the data while estimating the posterior over parameters. It is architecture-independent, and applies both to exact and approximate equivariances. As a real-world application, we use GNPE for amortized inference of astrophysical binary black hole systems from gravitational-wave observations. We show that GNPE achieves state-of-the-art accuracy while reducing inference times by three orders of magnitude.

Keyword spotting--or wakeword detection--is an essential feature for hands-free operation of modern voice-controlled devices. With such devices becoming ubiquitous, users might want to choose a personalized custom wakeword. In this work, we present DONUT, a CTC-based algorithm for online query-by-example keyword spotting that enables custom wakeword detection. The algorithm works by recording a small number of training examples from the user, generating a set of label sequence hypotheses from these training examples, and detecting the wakeword by aggregating the scores of all the hypotheses given a new audio recording. Our method combines the generalization and interpretability of CTC-based keyword spotting with the user-adaptation and convenience of a conventional query-by-example system. DONUT has low computational requirements and is well-suited for both learning and inference on embedded systems without requiring private user data to be uploaded to the cloud.

Supervised fine-tuning (SFT) plays a crucial role in adapting large language models (LLMs) to specific domains or tasks. However, as demonstrated by empirical experiments, the collected data inevitably contains noise in practical applications, which poses significant challenges to model performance on downstream tasks. Therefore, there is an urgent need for a noise-robust SFT framework to enhance model capabilities in downstream tasks. To address this challenge, we introduce a robust SFT framework (RobustFT) that performs noise detection and relabeling on downstream task data. For noise identification, our approach employs a multi-expert collaborative system with inference-enhanced models to achieve superior noise detection. In the denoising phase, we utilize a context-enhanced strategy, which incorporates the most relevant and confident knowledge followed by careful assessment to generate reliable annotations. Additionally, we introduce an effective data selection mechanism based on response entropy, ensuring only high-quality samples are retained for fine-tuning. Extensive experiments conducted on multiple LLMs across five datasets demonstrate RobustFT's exceptional performance in noisy scenarios.

The proliferation of LLM-based agents has led to increasing deployment of inter-agent collaboration for tasks like scheduling, negotiation, resource allocation etc. In such systems, privacy is critical, as agents often access proprietary tools and domain-specific databases requiring strict confidentiality. This paper examines whether LLM-based agents demonstrate an understanding of contextual privacy. And, if instructed, do these systems preserve inference time user privacy in non-adversarial multi-turn conversation. Existing benchmarks to evaluate contextual privacy in LLM-agents primarily assess single-turn, low-complexity tasks where private information can be easily excluded. We first present a benchmark - MAGPIE comprising 158 real-life high-stakes scenarios across 15 domains. These scenarios are designed such that complete exclusion of private data impedes task completion yet unrestricted information sharing could lead to substantial losses. We then evaluate the current state-of-the-art LLMs on (a) their understanding of contextually private data and (b) their ability to collaborate without violating user privacy. Empirical experiments demonstrate that current models, including GPT-4o and Claude-2.7-Sonnet, lack robust understanding of contextual privacy, misclassifying private data as shareable 25.2\% and 43.6\% of the time. In multi-turn conversations, these models disclose private information in 59.9\% and 50.5\% of cases even under explicit privacy instructions. Furthermore, multi-agent systems fail to complete tasks in 71\% of scenarios. These results underscore that current models are not aligned towards both contextual privacy preservation and collaborative task-solving.

Large language models (LLMs) are increasingly evaluated on formal tasks, where strong reasoning abilities define the state of the art. However, their ability to generalize to out-of-distribution problems remains limited. In this paper, we investigate how LLMs can achieve a systematic understanding of deductive rules. Our focus is on the task of identifying the appropriate subset of premises within a knowledge base needed to derive a given hypothesis. To tackle this challenge, we propose Meta-learning for In-context Deduction (MIND), a novel few-shot meta-learning fine-tuning approach. The goal of MIND is to enable models to generalize more effectively to unseen knowledge bases and to systematically apply inference rules. Our results show that MIND significantly improves generalization in small LMs ranging from 1.5B to 7B parameters. The benefits are especially pronounced in smaller models and low-data settings. Remarkably, small models fine-tuned with MIND outperform state-of-the-art LLMs, such as GPT-4o and o3-mini, on this task.

Control variates are variance reduction tools for Monte Carlo estimators. They can provide significant variance reduction, but usually require a large number of samples, which can be prohibitive when sampling or evaluating the integrand is computationally expensive. Furthermore, there are many scenarios where we need to compute multiple related integrals simultaneously or sequentially, which can further exacerbate computational costs. In this paper, we propose vector-valued control variates, an extension of control variates which can be used to reduce the variance of multiple Monte Carlo estimators jointly. This allows for the transfer of information across integration tasks, and hence reduces the need for a large number of samples. We focus on control variates based on kernel interpolants and our novel construction is obtained through a generalised Stein identity and the development of novel matrix-valued Stein reproducing kernels. We demonstrate our methodology on a range of problems including multifidelity modelling, Bayesian inference for dynamical systems, and model evidence computation through thermodynamic integration.

Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is particularly challenging to generate both human-like and informative responses in this setting. Recent research primarily focused on various knowledge distillation methods where the underlying relationship between the facts in a knowledge base is not effectively captured. In this paper, we go one step further and demonstrate how the structural information of a knowledge graph can improve the system's inference capabilities. Specifically, we propose DialoKG, a novel task-oriented dialogue system that effectively incorporates knowledge into a language model. Our proposed system views relational knowledge as a knowledge graph and introduces (1) a structure-aware knowledge embedding technique, and (2) a knowledge graph-weighted attention masking strategy to facilitate the system selecting relevant information during the dialogue generation. An empirical evaluation demonstrates the effectiveness of DialoKG over state-of-the-art methods on several standard benchmark datasets.

Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning (PEFT) technique for adapting large language models (LLMs) to downstream tasks. While prior work has explored strategies for integrating LLM training and serving, there still remains a gap in unifying fine-tuning and inference for LoRA-based models. We present Loquetier, a virtualized multi-LoRA framework that seamlessly integrates LoRA fine-tuning and serving within a single runtime. Loquetier introduces two key components: (1) a Virtualized Module that isolates PEFT-based modifications and supports multiple adapters on a shared base model, and (2) an optimized computation flow with a kernel design that merges fine-tuning and inference paths in forward propagation, enabling efficient batching and minimizing kernel invocation overhead. Extensive experiments across three task settings show that Loquetier consistently outperforms existing baselines in both performance and flexibility, achieving up to 3.0times the throughput of the state-of-the-art co-serving system on inference-only tasks and 46.4times higher SLO attainment than PEFT on unified fine-tuning and inference tasks. The implementation of Loquetier is publicly available at https://github.com/NJUDeepEngine/Loquetier.

Large Language Models (LLMs) are revolutionizing numerous industries, but their substantial computational demands create challenges for efficient deployment, particularly in cloud environments. Traditional approaches to inference serving often struggle with resource inefficiencies, leading to high operational costs, latency issues, and limited scalability. This article explores how Cloud Native technologies, such as containerization, microservices, and dynamic scheduling, can fundamentally improve LLM inference serving. By leveraging these technologies, we demonstrate how a Cloud Native system enables more efficient resource allocation, reduces latency, and enhances throughput in high-demand scenarios. Through real-world evaluations using Kubernetes-based autoscaling, we show that Cloud Native architectures can dynamically adapt to workload fluctuations, mitigating performance bottlenecks while optimizing LLM inference serving performance. This discussion provides a broader perspective on how Cloud Native frameworks could reshape the future of scalable LLM inference serving, offering key insights for researchers, practitioners, and industry leaders in cloud computing and artificial intelligence.

This paper proposes a methodology for discovering meaningful properties in data by exploring the latent space of unsupervised deep generative models. We combine manipulation of individual latent variables to extreme values with methods inspired by causal inference into an approach we call causal disentanglement with extreme values (CDEV) and show that this method yields insights for model interpretability. With this, we can test for what properties of unknown data the model encodes as meaningful, using it to glean insight into the communication system of sperm whales (Physeter macrocephalus), one of the most intriguing and understudied animal communication systems. The network architecture used has been shown to learn meaningful representations of speech; here, it is used as a learning mechanism to decipher the properties of another vocal communication system in which case we have no ground truth. The proposed methodology suggests that sperm whales encode information using the number of clicks in a sequence, the regularity of their timing, and audio properties such as the spectral mean and the acoustic regularity of the sequences. Some of these findings are consistent with existing hypotheses, while others are proposed for the first time. We also argue that our models uncover rules that govern the structure of units in the communication system and apply them while generating innovative data not shown during training. This paper suggests that an interpretation of the outputs of deep neural networks with causal inference methodology can be a viable strategy for approaching data about which little is known and presents another case of how deep learning can limit the hypothesis space. Finally, the proposed approach can be extended to other architectures and datasets.

Parameter-efficient finetuning (PEFT) is a widely used technique to adapt large language models for different tasks. Service providers typically create separate systems for users to perform PEFT model finetuning and inference tasks. This is because existing systems cannot handle workloads that include a mix of inference and PEFT finetuning requests. As a result, shared GPU resources are underutilized, leading to inefficiencies. To address this problem, we present FlexLLM, the first system that can serve inference and parameter-efficient finetuning requests in the same iteration. Our system leverages the complementary nature of these two tasks and utilizes shared GPU resources to run them jointly, using a method called co-serving. To achieve this, FlexLLM introduces a novel token-level finetuning mechanism, which breaks down the finetuning computation of a sequence into smaller token-level computations and uses dependent parallelization and graph pruning, two static compilation optimizations, to minimize the memory overhead and latency for co-serving. Compared to existing systems, FlexLLM's co-serving approach reduces the activation GPU memory overhead by up to 8x, and the end-to-end GPU memory requirement of finetuning by up to 36% while maintaining a low inference latency and improving finetuning throughput. For example, under a heavy inference workload, FlexLLM can still preserve more than 80% of the peak finetuning throughput, whereas existing systems cannot make any progress with finetuning. The source code of FlexLLM is publicly available at https://github.com/flexflow/FlexFlow.

Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified framework that covers several recent methods and their novel variants. We conduct comprehensive experiments on all the configurations of the framework, evaluating their generation throughput and performance in language modeling and downstream tasks. We find that when reducing the size of the KV cache by 2x, most configurations can achieve competitive performance to and higher throughput than standard transformers, but when further reducing the size of the KV cache, pairing queries of all layers with KVs of upper layers can better maintain performance, although it also introduces additional training cost and prefilling latency. We hope that this work will help users choose the appropriate approach according to their requirements and facilitate research on the acceleration of LLM inference.

We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus. In contrast to existing logic-based approaches, our system is intentionally designed to be as lightweight as possible, and operates using a small set of well-known (surface-level) monotonicity facts about quantifiers, lexical items and tokenlevel polarity information. Despite its simplicity, we find our approach to be competitive with other logic-based NLI models on the SICK benchmark. We also use MonaLog in combination with the current state-of-the-art model BERT in a variety of settings, including for compositional data augmentation. We show that MonaLog is capable of generating large amounts of high-quality training data for BERT, improving its accuracy on SICK.

Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making. With the rapid advancement of large language models (LLMs), reasoning has emerged as a key capability that distinguishes advanced AI systems from conventional models that empower chatbots. In this survey, we categorize existing methods along two orthogonal dimensions: (1) Regimes, which define the stage at which reasoning is achieved (either at inference time or through dedicated training); and (2) Architectures, which determine the components involved in the reasoning process, distinguishing between standalone LLMs and agentic compound systems that incorporate external tools, and multi-agent collaborations. Within each dimension, we analyze two key perspectives: (1) Input level, which focuses on techniques that construct high-quality prompts that the LLM condition on; and (2) Output level, which methods that refine multiple sampled candidates to enhance reasoning quality. This categorization provides a systematic understanding of the evolving landscape of LLM reasoning, highlighting emerging trends such as the shift from inference-scaling to learning-to-reason (e.g., DeepSeek-R1), and the transition to agentic workflows (e.g., OpenAI Deep Research, Manus Agent). Additionally, we cover a broad spectrum of learning algorithms, from supervised fine-tuning to reinforcement learning such as PPO and GRPO, and the training of reasoners and verifiers. We also examine key designs of agentic workflows, from established patterns like generator-evaluator and LLM debate to recent innovations. ...

Multi-agent systems (MAS) are critical for automating complex tasks, yet their practical deployment is severely hampered by the challenge of failure attribution. Current diagnostic tools, which rely on statistical correlations, are fundamentally inadequate; on challenging benchmarks like Who\&When, state-of-the-art methods achieve less than 15\% accuracy in locating the root-cause step of a failure. To address this critical gap, we introduce the first failure attribution framework for MAS grounded in multi-granularity causal inference. Our approach makes two key technical contributions: (1) a performance causal inversion principle, which correctly models performance dependencies by reversing the data flow in execution logs, combined with Shapley values to accurately assign agent-level blame; (2) a novel causal discovery algorithm, CDC-MAS, that robustly identifies critical failure steps by tackling the non-stationary nature of MAS interaction data. The framework's attribution results directly fuel an automated optimization loop, generating targeted suggestions whose efficacy is validated via counterfactual simulations. Evaluations on the Who\&When and TRAIL benchmarks demonstrate a significant leap in performance. Our method achieves up to 36.2\% step-level accuracy. Crucially, the generated optimizations boost overall task success rates by an average of 22.4\%. This work provides a principled and effective solution for debugging complex agent interactions, paving the way for more reliable and interpretable multi-agent systems.

Prompt engineering has emerged as a powerful technique for optimizing large language models (LLMs) for specific applications, enabling faster prototyping and improved performance, and giving rise to the interest of the community in protecting proprietary system prompts. In this work, we explore a novel perspective on prompt privacy through the lens of membership inference. We develop Prompt Detective, a statistical method to reliably determine whether a given system prompt was used by a third-party language model. Our approach relies on a statistical test comparing the distributions of two groups of model outputs corresponding to different system prompts. Through extensive experiments with a variety of language models, we demonstrate the effectiveness of Prompt Detective for prompt membership inference. Our work reveals that even minor changes in system prompts manifest in distinct response distributions, enabling us to verify prompt usage with statistical significance.

Large language models (LLMs) based on transformers have made significant strides in recent years, the success of which is driven by scaling up their model size. Despite their high algorithmic performance, the computational and memory requirements of LLMs present unprecedented challenges. To tackle the high compute requirements of LLMs, the Mixture-of-Experts (MoE) architecture was introduced which is able to scale its model size without proportionally scaling up its computational requirements. Unfortunately, MoE's high memory demands and dynamic activation of sparse experts restrict its applicability to real-world problems. Previous solutions that offload MoE's memory-hungry expert parameters to CPU memory fall short because the latency to migrate activated experts from CPU to GPU incurs high performance overhead. Our proposed Pre-gated MoE system effectively tackles the compute and memory challenges of conventional MoE architectures using our algorithm-system co-design. Pre-gated MoE employs our novel pre-gating function which alleviates the dynamic nature of sparse expert activation, allowing our proposed system to address the large memory footprint of MoEs while also achieving high performance. We demonstrate that Pre-gated MoE is able to improve performance, reduce GPU memory consumption, while also maintaining the same level of model quality. These features allow our Pre-gated MoE system to cost-effectively deploy large-scale LLMs using just a single GPU with high performance.

The Mixture-of-Experts (MoE) architecture has demonstrated significant advantages in the era of Large Language Models (LLMs), offering enhanced capabilities with reduced inference costs. However, deploying MoE-based LLMs on memoryconstrained edge devices remains challenging due to their substantial memory requirements. While existing expertoffloading methods alleviate the memory requirements, they often incur significant expert-loading costs or compromise model accuracy. We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency while preserving model accuracy. HOBBIT introduces three innovative techniques that map the natural hierarchy of MoE computation: (1) a token-level dynamic expert loading mechanism, (2) a layer-level adaptive expert prefetching technique, and (3) a sequence-level multidimensional expert caching policy. These innovations fully leverage the benefits of mixedprecision expert inference. By implementing HOBBIT on top of the renowned LLM inference framework Llama.cpp, we evaluate its performance across different edge devices with representative MoE models. The results demonstrate that HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.

This paper considers a joint scattering environment sensing and data recovery problem in an uplink integrated sensing and communication (ISAC) system. To facilitate joint scatterers localization and multi-user (MU) channel estimation, we introduce a three-dimensional (3D) location-domain sparse channel model to capture the joint sparsity of the MU channel (i.e., different user channels share partially overlapped scatterers). Then the joint problem is formulated as a bilinear structured sparse recovery problem with a dynamic position grid and imperfect parameters (such as time offset and user position errors). We propose an expectation maximization based turbo bilinear subspace variational Bayesian inference (EM-Turbo-BiSVBI) algorithm to solve the problem effectively, where the E-step performs Bayesian estimation of the the location-domain sparse MU channel by exploiting the joint sparsity, and the M-step refines the dynamic position grid and learns the imperfect factors via gradient update. Two methods are introduced to greatly reduce the complexity with almost no sacrifice on the performance and convergence speed: 1) a subspace constrained bilinear variational Bayesian inference (VBI) method is proposed to avoid any high-dimensional matrix inverse; 2) the multiple signal classification (MUSIC) and subspace constrained VBI methods are combined to obtain a coarse estimation result to reduce the search range. Simulations verify the advantages of the proposed scheme over baseline schemes.

The R-Learner is a powerful, theoretically-grounded framework for estimating heterogeneous treatment effects, prized for its robustness to nuisance model errors. However, its application to network data, where causal heterogeneity is often graph-dependent, presents a critical challenge to its core assumption of a well-specified final-stage model. In this paper, we conduct a large-scale empirical study to systematically dissect the R-Learner framework on graphs. We provide the first rigorous evidence that the primary driver of performance is the inductive bias of the final-stage CATE estimator, an effect that dominates the choice of nuisance models. Our central finding is the quantification of a catastrophic "representation bottleneck": we prove with overwhelming statistical significance (p < 0.001) that R-Learners with a graph-blind final stage fail completely (MSE > 4.0), even when paired with powerful GNN nuisance models. Conversely, our proposed end-to-end Graph R-Learner succeeds and significantly outperforms a strong, non-DML GNN T-Learner baseline. Furthermore, we identify and provide a mechanistic explanation for a subtle, topology-dependent "nuisance bottleneck," linking it to GNN over-squashing via a targeted "Hub-Periphery Trade-off" analysis. Our findings are validated across diverse synthetic and semi-synthetic benchmarks. We release our code as a reproducible benchmark to facilitate future research on this critical "final-stage bottleneck."

Failure attribution in multi-agent systems -- pinpointing the exact step where a decisive error occurs -- is a critical yet unsolved challenge. Current methods treat this as a pattern recognition task over long conversation logs, leading to critically low step-level accuracy (below 17\%), which renders them impractical for debugging complex systems. Their core weakness is a fundamental inability to perform robust counterfactual reasoning: to determine if correcting a single action would have actually averted the task failure. To bridge this counterfactual inference gap, we introduce Abduct-Act-Predict (A2P) Scaffolding, a novel agent framework that transforms failure attribution from pattern recognition into a structured causal inference task. A2P explicitly guides a large language model through a formal three-step reasoning process within a single inference pass: (1) Abduction, to infer the hidden root causes behind an agent's actions; (2) Action, to define a minimal corrective intervention; and (3) Prediction, to simulate the subsequent trajectory and verify if the intervention resolves the failure. This structured approach leverages the holistic context of the entire conversation while imposing a rigorous causal logic on the model's analysis. Our extensive experiments on the Who\&When benchmark demonstrate its efficacy. On the Algorithm-Generated dataset, A2P achieves 47.46\% step-level accuracy, a 2.85times improvement over the 16.67\% of the baseline. On the more complex Hand-Crafted dataset, it achieves 29.31\% step accuracy, a 2.43times improvement over the baseline's 12.07\%. By reframing the problem through a causal lens, A2P Scaffolding provides a robust, verifiable, and significantly more accurate solution for automated failure attribution. Ours code are released at https://github.com/ResearAI/A2P.

The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is vibrant, there hasn't been a concise framework that analyzes the various methods of LLM Inference to provide a clear understanding of this domain. Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model for systematic analysis of LLM inference techniques. This framework identifies the bottlenecks when deploying LLMs on hardware devices and provides a clear understanding of practical problems, such as why LLMs are memory-bound, how much memory and computation they need, and how to choose the right hardware. We systematically collate the latest advancements in efficient LLM inference, covering crucial areas such as model compression (e.g., Knowledge Distillation and Quantization), algorithm improvements (e.g., Early Exit and Mixture-of-Expert), and both hardware and system-level enhancements. Our survey stands out by analyzing these methods with roofline model, helping us understand their impact on memory access and computation. This distinctive approach not only showcases the current research landscape but also delivers valuable insights for practical implementation, positioning our work as an indispensable resource for researchers new to the field as well as for those seeking to deepen their understanding of efficient LLM deployment. The analyze tool, LLM-Viewer, is open-sourced.

Large language models (LLMs) are useful in many NLP tasks and become more capable with size, with the best open-source models having over 50 billion parameters. However, using these 50B+ models requires high-end hardware, making them inaccessible to most researchers. In this work, we investigate methods for cost-efficient inference and fine-tuning of LLMs, comparing local and distributed strategies. We observe that a large enough model (50B+) can run efficiently even on geodistributed devices in a consumer-grade network. This could allow running LLM efficiently by pooling together idle compute resources of multiple research groups and volunteers. We address two open problems: (1) how to perform inference and fine-tuning reliably if any device can disconnect abruptly and (2) how to partition LLMs between devices with uneven hardware, joining and leaving at will. In order to do that, we develop special fault-tolerant inference algorithms and load-balancing protocols that automatically assign devices to maximize the total system throughput. We showcase these algorithms in Petals - a decentralized system that runs Llama 2 (70B) and BLOOM (176B) over the Internet up to 10x faster than offloading for interactive generation. We evaluate the performance of our system in simulated conditions and a real-world setup spanning two continents.

Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates this landscape by introducing its own challenging trade-off: sophisticated Generative Reward Models (GenRMs) can be computationally prohibitive if naively integrated with LLMs at test-time, while simpler, faster methods may lack reliability. To overcome these challenges, we introduce FlexiVe, a novel generative verifier that flexibly balances computational resources between rapid, reliable fast thinking and meticulous slow thinking using a Flexible Allocation of Verification Budget strategy. We further propose the Solve-Detect-Verify pipeline, an efficient inference-time scaling framework that intelligently integrates FlexiVe, proactively identifying solution completion points to trigger targeted verification and provide focused solver feedback. Experiments show FlexiVe achieves superior accuracy in pinpointing errors within reasoning traces on ProcessBench. Furthermore, on challenging mathematical reasoning benchmarks (AIME 2024, AIME 2025, and CNMO), our full approach outperforms baselines like self-consistency in reasoning accuracy and inference efficiency. Our system offers a scalable and effective solution to enhance LLM reasoning at test time.

Enabling agentic AI systems to adapt their problem-solving approaches based on post-training interactions remains a fundamental challenge. While systems that update and maintain a memory at inference time have been proposed, existing designs only steer the system by modifying textual input to a language model or agent, which means that they cannot change sampling parameters, remove tools, modify system prompts, or switch between agentic and workflow paradigms. On the other hand, systems that adapt more flexibly require offline optimization and remain static once deployed. We present Experience-Guided Reasoner (EGuR), which generates tailored strategies -- complete computational procedures involving LLM calls, tools, sampling parameters, and control logic -- dynamically at inference time based on accumulated experience. We achieve this using an LLM-based meta-strategy -- a strategy that outputs strategies -- enabling adaptation of all strategy components (prompts, sampling parameters, tool configurations, and control logic). EGuR operates through two components: a Guide generates multiple candidate strategies conditioned on the current problem and structured memory of past experiences, while a Consolidator integrates execution feedback to improve future strategy generation. This produces complete, ready-to-run strategies optimized for each problem, which can be cached, retrieved, and executed as needed without wasting resources. Across five challenging benchmarks (AIME 2025, 3-SAT, and three Big Bench Extra Hard tasks), EGuR achieves up to 14% accuracy improvements over the strongest baselines while reducing computational costs by up to 111x, with both metrics improving as the system gains experience.

Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive optimizations for optimal performance. Current systems batch prefill and decoding to boost throughput but encounter latency issues, while others disaggregate these phases, leading to resource underutilization. We propose AcceLLM, a novel method addressing latency and load balancing, inspired by the cache data management. It strategically utilizes redundant data to enhance inference via load balancing and optimal hardware use. Simulated evaluations on Nvidia H100 GPU and Huawei Ascend 910B2 show AcceLLM surpasses state-of-the-art systems up to 30% in latency and efficiency, handling diverse workloads effectively.

Diffusion large language models (dLLMs) represent a significant advancement in text generation, offering parallel token decoding capabilities. However, existing open-source implementations suffer from quality-speed trade-offs that impede their practical deployment. Conservative sampling strategies typically decode only the most confident token per step to ensure quality (i.e., greedy decoding), at the cost of inference efficiency due to repeated redundant refinement iterations--a phenomenon we term delayed decoding. Through systematic analysis of dLLM decoding dynamics, we characterize this delayed decoding behavior and propose a training-free adaptive parallel decoding strategy, named LocalLeap, to address these inefficiencies. LocalLeap is built on two fundamental empirical principles: local determinism propagation centered on high-confidence anchors and progressive spatial consistency decay. By applying these principles, LocalLeap identifies anchors and performs localized relaxed parallel decoding within bounded neighborhoods, achieving substantial inference step reduction through early commitment of already-determined tokens without compromising output quality. Comprehensive evaluation on various benchmarks demonstrates that LocalLeap achieves 6.94times throughput improvements and reduces decoding steps to just 14.2\% of the original requirement, achieving these gains with negligible performance impact. The source codes are available at: https://github.com/friedrichor/LocalLeap.

Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details of state-of-the-art reasoning LLMs are concealed (such as in OpenAI o1 blog and DeepSeek R1 technical report), thus the community still struggles to reproduce their RL training results. We propose the Decoupled Clip and Dynamic sAmpling Policy Optimization (DAPO) algorithm, and fully open-source a state-of-the-art large-scale RL system that achieves 50 points on AIME 2024 using Qwen2.5-32B base model. Unlike previous works that withhold training details, we introduce four key techniques of our algorithm that make large-scale LLM RL a success. In addition, we open-source our training code, which is built on the verl framework, along with a carefully curated and processed dataset. These components of our open-source system enhance reproducibility and support future research in large-scale LLM RL.

Practical deployment of Multi-Agent Systems (MAS) demands strong test-time performance, motivating methods that guide inference-time search and selectively spend compute to improve quality. We present the Multi-Agent System Process Reward Model (MASPRM). It assigns per-action, per-agent values to partial inter-agent transcripts and acts as an inference-time controller. MASPRM is trained from multi-agent Monte Carlo Tree Search (MCTS) rollouts without requiring step-level human annotations, by propagating returns to local targets. At inference, MASPRM guides step-level beam search and MCTS, focusing computation on promising branches and pruning early. On GSM8K and MATH, MASPRM-guided decoding with an outcome reward model (ORM) applied to the final answer, improves exact match (EM) over a single straight-through MAS pass by +30.7 and +22.9 points, respectively. A MASPRM trained on GSM8K transfers zero-shot to MATH without retraining, adding 8.4 EM points at the same budget. MASPRM is a plug-in value model that estimates per-agent progress and complements verifier-style decoders, enabling more reliable, compute-aware multi-agent reasoning. Code: https://github.com/milad1378yz/MASPRM

The growing demand for efficient long-sequence modeling on edge devices has propelled widespread adoption of State Space Models (SSMs) like Mamba, due to their superior computational efficiency and scalability. As its autoregressive generation process remains memory-bound, speculative decoding has been proposed that incorporates draft model generation and target model verification. However, directly applying speculative decoding to SSMs faces three key challenges: (1) hidden state backtracking difficulties, (2) tree-based parallel verification incompatibility, and (3) hardware workload mismatch. To address these challenges, we propose SpecMamba, the first FPGA-based accelerator for Mamba with speculative decoding, which features system, algorithm, and hardware co-design. At the system level, we present a memory-aware hybrid backtracking strategy to coordinate both models. At the algorithm level, we propose first-in-first-out (FIFO)-based tree verification with tiling to minimize memory access. At the hardware level, we customize a dataflow that computes linear layers in parallel and SSM layers in series to enable maximal overlapping. Implemented on AMD FPGA platforms (VHK158 and VCK190), SpecMamba achieves a 2.27x speedup over GPU baselines and a 2.85x improvement compared to prior FPGA solutions, while demonstrating 5.41x and 1.26x higher energy efficiency, respectively.

The emergence of large-scale Mixture of Experts (MoE) models has marked a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, the deployment and inference of these models present substantial challenges in terms of computational resources, latency, and energy efficiency. This comprehensive survey systematically analyzes the current landscape of inference optimization techniques for MoE models across the entire system stack. We first establish a taxonomical framework that categorizes optimization approaches into model-level, system-level, and hardware-level optimizations. At the model level, we examine architectural innovations including efficient expert design, attention mechanisms, various compression techniques such as pruning, quantization, and knowledge distillation, as well as algorithm improvement including dynamic routing strategies and expert merging methods. At the system level, we investigate distributed computing approaches, load balancing mechanisms, and efficient scheduling algorithms that enable scalable deployment. Furthermore, we delve into hardware-specific optimizations and co-design strategies that maximize throughput and energy efficiency. This survey not only provides a structured overview of existing solutions but also identifies key challenges and promising research directions in MoE inference optimization. Our comprehensive analysis serves as a valuable resource for researchers and practitioners working on large-scale deployment of MoE models in resource-constrained environments. To facilitate ongoing updates and the sharing of cutting-edge advances in MoE inference optimization research, we have established a repository accessible at https://github.com/MoE-Inf/awesome-moe-inference/.

Energy efficiency of Convolutional Neural Networks (CNNs) has become an important area of research, with various strategies being developed to minimize the power consumption of these models. Previous efforts, including techniques like model pruning, quantization, and hardware optimization, have made significant strides in this direction. However, there remains a need for more effective on device AI solutions that balance energy efficiency with model performance. In this paper, we propose a novel approach to reduce the energy requirements of inference of CNNs. Our methodology employs two small Complementary CNNs that collaborate with each other by covering each other's "weaknesses" in predictions. If the confidence for a prediction of the first CNN is considered low, the second CNN is invoked with the aim of producing a higher confidence prediction. This dual-CNN setup significantly reduces energy consumption compared to using a single large deep CNN. Additionally, we propose a memory component that retains previous classifications for identical inputs, bypassing the need to re-invoke the CNNs for the same input, further saving energy. Our experiments on a Jetson Nano computer demonstrate an energy reduction of up to 85.8% achieved on modified datasets where each sample was duplicated once. These findings indicate that leveraging a complementary CNN pair along with a memory component effectively reduces inference energy while maintaining high accuracy.

Added toxicity in the context of translation refers to the fact of producing a translation output with more toxicity than there exists in the input. In this paper, we present MinTox which is a novel pipeline to identify added toxicity and mitigate this issue which works at inference time. MinTox uses a toxicity detection classifier which is multimodal (speech and text) and works in languages at scale. The mitigation method is applied to languages at scale and directly in text outputs. MinTox is applied to SEAMLESSM4T, which is the latest multimodal and massively multilingual machine translation system. For this system, MinTox achieves significant added toxicity mitigation across domains, modalities and language directions. MinTox manages to approximately filter out from 25% to 95% of added toxicity (depending on the modality and domain) while keeping translation quality.

Large Language Models (LLMs) based on Mixture-of-Experts (MoE) architecture are showing promising performance on various tasks. However, running them on resource-constrained settings, where GPU memory resources are not abundant, is challenging due to huge model sizes. Existing systems that offload model weights to CPU memory suffer from the significant overhead of frequently moving data between CPU and GPU. In this paper, we propose Fiddler, a resource-efficient inference engine with CPU-GPU orchestration for MoE models. The key idea of Fiddler is to use the computation ability of the CPU to minimize the data movement between the CPU and GPU. Our evaluation shows that Fiddler can run the uncompressed Mixtral-8x7B model, which exceeds 90GB in parameters, to generate over 3 tokens per second on a single GPU with 24GB memory, showing an order of magnitude improvement over existing methods. The code of Fiddler is publicly available at https://github.com/efeslab/fiddler

Text-to-Image (T2I) models have advanced rapidly, yet they remain vulnerable to semantic leakage, the unintended transfer of semantically related features between distinct entities. Existing mitigation strategies are often optimization-based or dependent on external inputs. We introduce DeLeaker, a lightweight, optimization-free inference-time approach that mitigates leakage by directly intervening on the model's attention maps. Throughout the diffusion process, DeLeaker dynamically reweights attention maps to suppress excessive cross-entity interactions while strengthening the identity of each entity. To support systematic evaluation, we introduce SLIM (Semantic Leakage in IMages), the first dataset dedicated to semantic leakage, comprising 1,130 human-verified samples spanning diverse scenarios, together with a novel automatic evaluation framework. Experiments demonstrate that DeLeaker consistently outperforms all baselines, even when they are provided with external information, achieving effective leakage mitigation without compromising fidelity or quality. These results underscore the value of attention control and pave the way for more semantically precise T2I models.

Large language models (LLMs) with hundreds of billions of parameters have sparked a new wave of exciting AI applications. However, they are computationally expensive at inference time. Sparsity is a natural approach to reduce this cost, but existing methods either require costly retraining, have to forgo LLM's in-context learning ability, or do not yield wall-clock time speedup on modern hardware. We hypothesize that contextual sparsity, which are small, input-dependent sets of attention heads and MLP parameters that yield approximately the same output as the dense model for a given input, can address these issues. We show that contextual sparsity exists, that it can be accurately predicted, and that we can exploit it to speed up LLM inference in wall-clock time without compromising LLM's quality or in-context learning ability. Based on these insights, we propose DejaVu, a system that uses a low-cost algorithm to predict contextual sparsity on the fly given inputs to each layer, along with an asynchronous and hardware-aware implementation that speeds up LLM inference. We validate that DejaVu can reduce the inference latency of OPT-175B by over 2X compared to the state-of-the-art FasterTransformer, and over 6X compared to the widely used Hugging Face implementation, without compromising model quality. The code is available at https://github.com/FMInference/DejaVu.

This paper presents our system description and error analysis of our entry for NLLP 2024 shared task on Legal Natural Language Inference (L-NLI) hagag2024legallenssharedtask2024. The task required classifying these relationships as entailed, contradicted, or neutral, indicating any association between the review and the complaint. Our system emerged as the winning submission, significantly outperforming other entries with a substantial margin and demonstrating the effectiveness of our approach in legal text analysis. We provide a detailed analysis of the strengths and limitations of each model and approach tested, along with a thorough error analysis and suggestions for future improvements. This paper aims to contribute to the growing field of legal NLP by offering insights into advanced techniques for natural language inference in legal contexts, making it accessible to both experts and newcomers in the field.

The Transformer architecture has significantly advanced natural language processing (NLP) and has been foundational in developing large language models (LLMs) such as LLaMA and OPT, which have come to dominate a broad range of NLP tasks. Despite their superior accuracy, LLMs present unique challenges in practical inference, concerning the compute and memory-intensive nature. Thanks to the autoregressive characteristic of LLM inference, KV caching for the attention layers in Transformers can effectively accelerate LLM inference by substituting quadratic-complexity computation with linear-complexity memory accesses. Yet, this approach requires increasing memory as demand grows for processing longer sequences. The overhead leads to reduced throughput due to I/O bottlenecks and even out-of-memory errors, particularly on resource-constrained systems like a single commodity GPU. In this paper, we propose ALISA, a novel algorithm-system co-design solution to address the challenges imposed by KV caching. On the algorithm level, ALISA prioritizes tokens that are most important in generating a new token via a Sparse Window Attention (SWA) algorithm. SWA introduces high sparsity in attention layers and reduces the memory footprint of KV caching at negligible accuracy loss. On the system level, ALISA employs three-phase token-level dynamical scheduling and optimizes the trade-off between caching and recomputation, thus maximizing the overall performance in resource-constrained systems. In a single GPU-CPU system, we demonstrate that under varying workloads, ALISA improves the throughput of baseline systems such as FlexGen and vLLM by up to 3X and 1.9X, respectively.

Generating texts with a large language model (LLM) consumes massive amounts of memory. Apart from the already-large model parameters, the key/value (KV) cache that holds information about previous tokens in a sequence can grow to be even larger than the model itself. This problem is exacerbated in one of the current LLM serving frameworks which reserves the maximum sequence length of memory for the KV cache to guarantee generating a complete sequence as they do not know the output sequence length. This restricts us to use a smaller batch size leading to lower GPU utilization and above all, lower throughput. We argue that designing a system with a priori knowledge of the output sequence can mitigate this problem. To this end, we propose S^{3}, which predicts the output sequence length, schedules generation queries based on the prediction to increase device resource utilization and throughput, and handle mispredictions. Our proposed method achieves 6.49times throughput over those systems that assume the worst case for the output sequence length.

Robust perception and dynamics modeling are fundamental to real-world robotic policy learning. Recent methods employ video diffusion models (VDMs) to enhance robotic policies, improving their understanding and modeling of the physical world. However, existing approaches overlook the coherent and physically consistent motion representations inherently encoded across frames in VDMs. To this end, we propose Video2Act, a framework that efficiently guides robotic action learning by explicitly integrating spatial and motion-aware representations. Building on the inherent representations of VDMs, we extract foreground boundaries and inter-frame motion variations while filtering out background noise and task-irrelevant biases. These refined representations are then used as additional conditioning inputs to a diffusion transformer (DiT) action head, enabling it to reason about what to manipulate and how to move. To mitigate inference inefficiency, we propose an asynchronous dual-system design, where the VDM functions as the slow System 2 and the DiT head as the fast System 1, working collaboratively to generate adaptive actions. By providing motion-aware conditions to System 1, Video2Act maintains stable manipulation even with low-frequency updates from the VDM. For evaluation, Video2Act surpasses previous state-of-the-art VLA methods by 7.7% in simulation and 21.7% in real-world tasks in terms of average success rate, further exhibiting strong generalization capabilities.

The rapid growth of large-scale AI models, particularly large language models has brought significant challenges in data privacy, computational resources, and accessibility. Traditional centralized architectures often struggle to meet required data security and scalability needs which hinders the democratization of AI systems. Nesa introduces a model-agnostic sharding framework designed for decentralized AI inference. Our framework uses blockchain-based sequential deep neural network sharding to distribute computational tasks across a diverse network of nodes based on a personalised heuristic and routing mechanism. This enables efficient distributed training and inference for recent large-scale models even on consumer-grade hardware. We use compression techniques like dynamic blockwise quantization and mixed matrix decomposition to reduce data transfer and memory needs. We also integrate robust security measures, including hardware-based trusted execution environments to ensure data integrity and confidentiality. Evaluating our system across various natural language processing and vision tasks shows that these compression strategies do not compromise model accuracy. Our results highlight the potential to democratize access to cutting-edge AI technologies by enabling secure and efficient inference on a decentralized network.

Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI across various industries. Industry and research community have witnessed a large number of new applications, based on those foundation models. Such applications include question and answer, customer services, image and video generation, and code completions, among others. However, as the number of model parameters reaches to hundreds of billions, their deployment incurs prohibitive inference costs and high latency in real-world scenarios. As a result, the demand for cost-effective and fast inference using AI accelerators is ever more higher. To this end, our tutorial offers a comprehensive discussion on complementary inference optimization techniques using AI accelerators. Beginning with an overview of basic Transformer architectures and deep learning system frameworks, we deep dive into system optimization techniques for fast and memory-efficient attention computations and discuss how they can be implemented efficiently on AI accelerators. Next, we describe architectural elements that are key for fast transformer inference. Finally, we examine various model compression and fast decoding strategies in the same context.

We present MidasTouch, a tactile perception system for online global localization of a vision-based touch sensor sliding on an object surface. This framework takes in posed tactile images over time, and outputs an evolving distribution of sensor pose on the object's surface, without the need for visual priors. Our key insight is to estimate local surface geometry with tactile sensing, learn a compact representation for it, and disambiguate these signals over a long time horizon. The backbone of MidasTouch is a Monte-Carlo particle filter, with a measurement model based on a tactile code network learned from tactile simulation. This network, inspired by LIDAR place recognition, compactly summarizes local surface geometries. These generated codes are efficiently compared against a precomputed tactile codebook per-object, to update the pose distribution. We further release the YCB-Slide dataset of real-world and simulated forceful sliding interactions between a vision-based tactile sensor and standard YCB objects. While single-touch localization can be inherently ambiguous, we can quickly localize our sensor by traversing salient surface geometries. Project page: https://suddhu.github.io/midastouch-tactile/

Existing datasets for natural language inference (NLI) have propelled research on language understanding. We propose a new method for automatically deriving NLI datasets from the growing abundance of large-scale question answering datasets. Our approach hinges on learning a sentence transformation model which converts question-answer pairs into their declarative forms. Despite being primarily trained on a single QA dataset, we show that it can be successfully applied to a variety of other QA resources. Using this system, we automatically derive a new freely available dataset of over 500k NLI examples (QA-NLI), and show that it exhibits a wide range of inference phenomena rarely seen in previous NLI datasets.

3D graphics editing is crucial in applications like movie production and game design, yet it remains a time-consuming process that demands highly specialized domain expertise. Automating this process is challenging because graphical editing requires performing a variety of tasks, each requiring distinct skill sets. Recently, vision-language models (VLMs) have emerged as a powerful framework for automating the editing process, but their development and evaluation are bottlenecked by the lack of a comprehensive benchmark that requires human-level perception and presents real-world editing complexity. In this work, we present BlenderGym, the first comprehensive VLM system benchmark for 3D graphics editing. BlenderGym evaluates VLM systems through code-based 3D reconstruction tasks. We evaluate closed- and open-source VLM systems and observe that even the state-of-the-art VLM system struggles with tasks relatively easy for human Blender users. Enabled by BlenderGym, we study how inference scaling techniques impact VLM's performance on graphics editing tasks. Notably, our findings reveal that the verifier used to guide the scaling of generation can itself be improved through inference scaling, complementing recent insights on inference scaling of LLM generation in coding and math tasks. We further show that inference compute is not uniformly effective and can be optimized by strategically distributing it between generation and verification.

Recent advances in Visual Language Models (VLMs) have demonstrated exceptional performance in visual reasoning tasks. However, geo-localization presents unique challenges, requiring the extraction of multigranular visual cues from images and their integration with external world knowledge for systematic reasoning. Current approaches to geo-localization tasks often lack robust reasoning mechanisms and explainability, limiting their effectiveness. To address these limitations, we propose the Geo Reason Enhancement (GRE) Suite, a novel framework that augments VLMs with structured reasoning chains for accurate and interpretable location inference. The GRE Suite is systematically developed across three key dimensions: dataset, model, and benchmark. First, we introduce GRE30K, a high-quality geo-localization reasoning dataset designed to facilitate fine-grained visual and contextual analysis. Next, we present the GRE model, which employs a multi-stage reasoning strategy to progressively infer scene attributes, local details, and semantic features, thereby narrowing down potential geographic regions with enhanced precision. Finally, we construct the Geo Reason Evaluation Benchmark (GREval-Bench), a comprehensive evaluation framework that assesses VLMs across diverse urban, natural, and landmark scenes to measure both coarse-grained (e.g., country, continent) and fine-grained (e.g., city, street) localization performance. Experimental results demonstrate that GRE significantly outperforms existing methods across all granularities of geo-localization tasks, underscoring the efficacy of reasoning-augmented VLMs in complex geographic inference. Code and data will be released at https://github.com/Thorin215/GRE.

Relational graph neural networks (RGNNs) are graph neural networks (GNNs) with dedicated structures for modeling the different types of nodes and/or edges in heterogeneous graphs. While RGNNs have been increasingly adopted in many real-world applications due to their versatility and accuracy, they pose performance and system design challenges due to their inherent computation patterns, gap between the programming interface and kernel APIs, and heavy programming efforts in optimizing kernels caused by their coupling with data layout and heterogeneity. To systematically address these challenges, we propose Pigeon, a novel two-level intermediate representation (IR) and its code generator framework, that (a) represents the key properties of the RGNN models to bridge the gap between the programming interface and kernel APIs, (b) decouples model semantics, data layout, and operators-specific optimization from each other to reduce programming efforts, (c) expresses and leverages optimization opportunities in inter-operator transforms, data layout, and operator-specific schedules. By building on one general matrix multiply (GEMM) template and a node/edge traversal template, Pigeon achieves up to 7.8x speed-up in inference and 5.6x speed-up in training compared with the state-of-the-art public systems in select models, i.e., RGCN, RGAT, HGT, when running heterogeneous graphs provided by Deep Graph Library (DGL) and Open Graph Benchmark (OGB). Pigeon also triggers fewer out-of-memory (OOM) errors. In addition, we propose linear operator fusion and compact materialization to further accelerate the system by up to 2.2x.

The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial for complex tasks, present challenges in scalability, reliability, and potential misuse. Decentralized systems offer a solution by distributing workload and mitigating central points of failure, but they introduce risks of unauthorized access to sensitive data across nodes. We address these challenges with a comprehensive framework designed for responsible AI development. Our approach incorporates: 1) Zero-knowledge proofs for secure model verification, enhancing trust without compromising privacy. 2) Consensus-based verification checks to ensure consistent outputs across nodes, mitigating hallucinations and maintaining model integrity. 3) Split Learning techniques that segment models across different nodes, preserving data privacy by preventing full data access at any point. 4) Hardware-based security through trusted execution environments (TEEs) to protect data and computations. This framework aims to enhance security and privacy and improve the reliability and fairness of multimodal AI systems. Promoting efficient resource utilization contributes to more sustainable AI development. Our state-of-the-art proofs and principles demonstrate the framework's effectiveness in responsibly democratizing artificial intelligence, offering a promising approach for building secure and private foundational models.

Recent advances in synthetic data generation (SDG) have been hailed as a solution to the difficult problem of sharing sensitive data while protecting privacy. SDG aims to learn statistical properties of real data in order to generate "artificial" data that are structurally and statistically similar to sensitive data. However, prior research suggests that inference attacks on synthetic data can undermine privacy, but only for specific outlier records. In this work, we introduce a new attribute inference attack against synthetic data. The attack is based on linear reconstruction methods for aggregate statistics, which target all records in the dataset, not only outliers. We evaluate our attack on state-of-the-art SDG algorithms, including Probabilistic Graphical Models, Generative Adversarial Networks, and recent differentially private SDG mechanisms. By defining a formal privacy game, we show that our attack can be highly accurate even on arbitrary records, and that this is the result of individual information leakage (as opposed to population-level inference). We then systematically evaluate the tradeoff between protecting privacy and preserving statistical utility. Our findings suggest that current SDG methods cannot consistently provide sufficient privacy protection against inference attacks while retaining reasonable utility. The best method evaluated, a differentially private SDG mechanism, can provide both protection against inference attacks and reasonable utility, but only in very specific settings. Lastly, we show that releasing a larger number of synthetic records can improve utility but at the cost of making attacks far more effective.

A machine learning system can score well on a given test set by relying on heuristics that are effective for frequent example types but break down in more challenging cases. We study this issue within natural language inference (NLI), the task of determining whether one sentence entails another. We hypothesize that statistical NLI models may adopt three fallible syntactic heuristics: the lexical overlap heuristic, the subsequence heuristic, and the constituent heuristic. To determine whether models have adopted these heuristics, we introduce a controlled evaluation set called HANS (Heuristic Analysis for NLI Systems), which contains many examples where the heuristics fail. We find that models trained on MNLI, including BERT, a state-of-the-art model, perform very poorly on HANS, suggesting that they have indeed adopted these heuristics. We conclude that there is substantial room for improvement in NLI systems, and that the HANS dataset can motivate and measure progress in this area