Cheng Wan 3c06b673af [8/N] MoE Refactor: deprecate EPMoE (#11211)

2025-10-07 21:51:41 -07:00

..

all_reduce

[Feat] Support Torch Symm Mem AllReduce (#10571)

2025-10-05 13:55:19 -07:00

decoding_attention_triton

…

deepep

…

deepseek

Restruct sgl-kernel benchmark (#10861)

2025-09-25 07:45:25 +08:00

elementwise

[sgl-kernel] Optimize concat_mla_k kernel (#10543)

2025-09-28 23:04:22 +08:00

flashinfer_allreduce_fusion

[benchmark] add flashinfer_allreduce_fusion benchmark (#9937)

2025-09-03 16:31:01 +08:00

fused_moe_triton

[sgl-kernel] Support float64 moe_sum_reduce cuda kernel (#11068)

2025-10-07 14:31:11 +00:00

minmax-text-01-lightning_attention

…

quantization

…

scheduler_batch

…

sliding_window_attention_triton

…