4 people 405bc86768 [Perf] Launch the top-k/top-p Triton sampler kernel with 8 warps (#51507) ...

Signed-off-by: BabyDrangoner <148877251+BabyDrangoner@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-08-10 10:55:35 -07:00

..

__init__.py

[V1] Use FlashInfer Sampling Kernel for Top-P & Top-K Sampling (#11394)

2024-12-27 09:32:38 +09:00

bad_words.py

[Perf][1/n] Eliminate various GPU<->CPU syncs (#41429)

2026-05-11 20:36:03 +00:00

logprobs.py

[Performance Improvement] Update batched_count_greater_than to handle batch size 1 without recompile (#38933)

2026-04-09 23:51:31 +08:00

penalties.py

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

topk_topp_sampler.py

Enable gfx1250 ROCm architecture (#46516)

2026-07-31 01:41:12 +00:00

topk_topp_triton.py

[Perf] Launch the top-k/top-p Triton sampler kernel with 8 warps (#51507)

2026-08-10 10:55:35 -07:00