-
Peking university
- Beijing
- xunhaolai.github.io
Pinned Loading
-
ByteDance-Seed/FlexPrefill
ByteDance-Seed/FlexPrefill PublicCode for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
-
native-sparse-attention-triton
native-sparse-attention-triton PublicEfficient triton implementation of Native Sparse Attention.
-
ring-sliding-window-attention
ring-sliding-window-attention PublicRing sliding window attention implementation with flash attention
Python 8
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.

