zijie-tian/nano-vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
161 Commits 3 Branches 0 Tags
47d237bb7e055b8b975273252e99e274e6a89271
Commit Graph

2 Commits

Author SHA1 Message Date
Zijie Tian
bc92c1fdb8 feat: add xattn_estimate_chunked for chunked prefill support 
- Add xattn_estimate_chunked function ported from COMPASS
- Support chunked prefill with q_start_pos parameter
- Ensure 100% consistency with standard xattn_estimate when
  using matching chunk_size parameter
- Add test and documentation

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 01:13:17 +08:00
Zijie Tian
3aef6fc3a2 ✨ feat: add XAttention Triton operators for sparse attention estimation 
Port XAttention operators from COMPASS project:
- flat_group_gemm_fuse_reshape: stride reshape GEMM kernel
- softmax_fuse_block_sum: fused softmax with block-level summation
- xattn_estimate: main estimation function for block sparse attention
- find_blocks_chunked: cumulative threshold-based block selection

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-20 04:27:07 +08:00