GraphPKU

AI & ML interests

None defined yet.

Recent Activity

billyisavailable  authored a paper about 2 months ago

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill \& Decode Inference

billyisavailable  authored a paper about 2 months ago

LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?

billyisavailable  authored a paper about 2 months ago

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

View all activity

Team members 3