hlu1 5f1eb20484 [chore] Remove unused ep_moe cuda kernels (#9956)

2025-09-06 01:35:50 -07:00

..

testing

…

__init__.py

[chore] Remove unused ep_moe cuda kernels (#9956)

2025-09-06 01:35:50 -07:00

allreduce.py

…

attention.py

…

cutlass_moe.py

…

elementwise.py

Support copying tensor from cpu to gpu without using copy engines (#10007)

2025-09-05 20:07:19 +08:00

flash_attn.py

Reduce overhead for fa by not calling heavy CUDA property check (#7375)

2025-08-20 16:26:28 +08:00

fused_moe.py

Minor style fixes for sgl-kernel (#9289)

2025-08-18 09:38:35 -07:00

gemm.py

[1/2] Optimizations and refactors about quant kernel (#9534)

2025-09-05 18:45:08 +08:00

grammar.py

…

kvcacheio.py

[AMD] Support Hierarchical Caching on AMD GPUs (#8236)

2025-08-28 15:27:07 -07:00

marlin.py

…

memory.py

…

moe.py

[chore] Remove unused ep_moe cuda kernels (#9956)

2025-09-06 01:35:50 -07:00

sampling.py

Minor style fixes for sgl-kernel (#9289)

2025-08-18 09:38:35 -07:00

scalar_type.py

…

sparse_flash_attn.py

…

spatial.py

…

speculative.py

…

test_utils.py

[1/2] Optimizations and refactors about quant kernel (#9534)

2025-09-05 18:45:08 +08:00

top_k.py

…

utils.py

[fix] fix enable_pdl for blackwell (#9011)

2025-08-19 01:16:08 +08:00

version.py

chore: bump v0.3.8 sgl-kernel (#9907)

2025-09-02 01:27:26 -07:00