Yi Pan 2c894d25be feat: support green ctx creation by a list of SM counts (#1190)

2025-06-30 00:29:42 -07:00

..

activation.rst

bugfix: Fix Documentation Build Proces (#655)

2024-12-11 23:11:39 -08:00

cascade.rst

bugfix: Fix Documentation Build Proces (#655)

2024-12-11 23:11:39 -08:00

decode.rst

doc: improve mla related documentation (#818)

2025-02-12 23:59:54 -08:00

gemm.rst

perf: accelerate blackwell grouped gemm (#1086)

2025-05-22 23:38:35 -07:00

green_ctx.rst

feat: support green ctx creation by a list of SM counts (#1190)

2025-06-30 00:29:42 -07:00

logits_processor.rst

doc: fix LogitsPipe example (#1110)

2025-06-02 23:26:17 -07:00

mla.rst

doc: Fix the incorrect DeepSeek-V3 paper link (#826)

2025-02-13 11:31:06 -08:00

norm.rst

bugfix: Fix Documentation Build Proces (#655)

2024-12-11 23:11:39 -08:00

page.rst

feat: support mla kvcache store (#888)

2025-03-13 11:23:07 -07:00

prefill.rst

bugfix: Fix Documentation Build Proces (#655)

2024-12-11 23:11:39 -08:00

quantization.rst

bugfix: Fix Documentation Build Proces (#655)

2024-12-11 23:11:39 -08:00

rope.rst

bugfix: Fix Documentation Build Proces (#655)

2024-12-11 23:11:39 -08:00

sampling.rst

bugfix: Fix Documentation Build Proces (#655)

2024-12-11 23:11:39 -08:00

sparse.rst

[feat] support block sparse attention w/ variable block sizes and head-wise sparse patterns (#1177)

2025-06-26 17:37:57 -07:00