Wentao Ye 3a6d5cbefd [Perf] Optimize dcp allocate tensor (#33102) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>

2026-01-27 17:24:41 -05:00

..

__init__.py

…

chunked_prefill_paged_decode.py

Fix IndexError with encoder-decoder models when using Custom Paged Attention (#33112)

2026-01-27 10:33:37 +08:00

common.py

[Perf] Optimize dcp allocate tensor (#33102)

2026-01-27 17:24:41 -05:00

flashmla.py

[FlashMLA] Update FlashMLA to expose new arguments (#32810)

2026-01-21 22:02:39 -07:00

merge_attn_states.py

…

paged_attn.py

[2/N][Attention] Fix pre-commit errors (#32052)

2026-01-10 00:27:15 +00:00

prefix_prefill.py

…

rocm_aiter_mla_sparse.py

[ROCm][Deepseekv3.2] Refactor Sparse Indexer as CustomOp (#29287)

2026-01-21 23:16:30 +08:00

triton_decode_attention.py

…

triton_merge_attn_states.py

…

triton_prefill_attention.py

[Performance] Improve Triton prefill attention kernel's performance (#32403)

2026-01-17 20:19:59 -08:00

triton_reshape_and_cache_flash.py

…

triton_unified_attention.py

[Model] Support Step1 Model (#32511)

2026-01-18 10:20:46 +00:00

vit_attn_wrappers.py

[Misc][LLaMa4] Compile LLaMa Vision Encoder (#30709)

2026-01-09 22:01:38 -05:00