Uranus 982db4ebac Feat: GLM-4.6 supports shared experts fusion (#13873) ...

Signed-off-by: UranusSeven <109661872+UranusSeven@users.noreply.github.com>
Co-authored-by: Kevin-XiongC <kevin_xiong1997@outlook.com>
Co-authored-by: Mingyi Jin <jinmingyi1998@sina.cn>

2025-12-01 11:33:18 +08:00

..

all_reduce

[AMD] Add AITER Custom All-Reduce (#13102)

2025-11-12 21:53:44 -08:00

decoding_attention_triton

[CI] Remove unused imports with Ruff to pre-commit config, only to benchmarks/docs/examples folder (#3969)

2025-03-27 19:45:02 -07:00

deepep

fix(deepep): resolve benchmark failure on 4×IB-card setup by aligning tuning config with DeepEP commit bdd119f8 (#11965)

2025-10-22 21:20:54 -07:00

deepseek

[NVIDIA] Add fp8 gemm benchmark on blackwell (#13528)

2025-11-19 19:35:00 -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

Feat: GLM-4.6 supports shared experts fusion (#13873)

2025-12-01 11:33:18 +08:00

quantization

Replace [silu_and_mul_]scaled_fp4_group_quant by Flashinfer equivalent (#12376)

2025-11-13 00:26:00 -08:00

scheduler_batch

[test] add ut and bm for get_last_loc (#6746)

2025-05-29 11:47:21 -07:00

sliding_window_attention_triton

Optimize triton swa kernel by skipping computation (#8860)

2025-08-06 21:37:50 +08:00