Yuan Luo afebb7ab78 Optimize custom-all-reduce (#17674) ...

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>

2026-02-01 18:59:31 +08:00

..

allreduce

Optimize custom-all-reduce (#17674)

2026-02-01 18:59:31 +08:00

attention

…

cpu

[CPU][INT4] Add INT4 kernels for CPU (#8226)

2026-01-29 22:30:13 -08:00

cutlass_extensions

…

elementwise

Reduce topk kernel shared memory from 128KB to 32KB for better occupancy (#17747)

2026-01-30 21:42:21 -08:00

expert_specialization

[sgl-kernel][Feat][B200][1/N] Support MXFP8 Grouped GEMM in Blackwell (#13731)

2025-12-04 10:09:09 +08:00

gemm

[NVIDIA] Fix CUDA arch requirement in nvfp4 cast (#12581)

2026-01-21 20:21:11 -08:00

grammar

…

kvcacheio

…

mamba

…

memory

…

moe

[perf]optimize w4afp8 kernel on deepseek-v3-0324 (#12921)

2025-12-18 18:13:22 +08:00

quantization/gguf

…

spatial

…

speculative

…

common_extension_musa.cc

[MUSA][2/N] sgl-kernel build (#17053)

2026-01-23 14:41:47 -08:00

common_extension_rocm.cc

[Diffusion] Delete sgl-kernel outdated time_embedding kernel (#17278)

2026-01-28 14:18:53 +08:00

common_extension.cc

[Diffusion] Delete sgl-kernel outdated time_embedding kernel (#17278)

2026-01-28 14:18:53 +08:00

flash_extension.cc

…

flashmla_extension.cc

…

spatial_extension.cc

…