wenhua cheng's picture

wenhua cheng

wenhuach

·

wenhuach21

AI & ML interests

Model Compression, CV

Recent Activity

reacted to their post with 🔥 2 days ago

🚀 SignRoundV2 for LLM quantization: PTQ-level cost, QAT-level accuracy — yes, even at 2 bits. https://huggingface.co/papers/2512.04746

new activity 2 days ago

Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound:Improve model card: Add pipeline tag, library name, and update paper/citation

authored a paper 4 days ago

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

View all activity

Organizations

upvoted a paper 4 days ago

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

Paper • 2512.04746 • Published 5 days ago • 11

upvoted an article 7 months ago

Article

Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs

+7

Apr 29

•

43

upvoted 3 collections 12 months ago

QWEN-AutoRound

20 items • Updated May 27 • 3

VLMs-AutoRound

23 items • Updated May 27 • 3

Llama-AutoRound

10 items • Updated Dec 30, 2024 • 3

upvoted a paper over 1 year ago

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs

Paper • 2309.05516 • Published Sep 11, 2023 • 10