Chunyuan WU 8fcc69e7c4 Turn on shm_allreduce and shm_allgather for fp16 (#10725)

2025-10-17 12:35:20 -07:00

..

test_activation.py

[CPU] Add gelu_and_mul kernel in sgl-kernel and add ut (#9300)

2025-09-08 23:23:13 -07:00

test_binding.py

…

test_comm.py

Turn on shm_allreduce and shm_allgather for fp16 (#10725)

2025-10-17 12:35:20 -07:00

test_cpu_graph.py

Split test_intel_amx_attention_backend.py to pass CI of timeout (#11370)

2025-10-15 19:22:32 -07:00

test_decode.py

…

test_extend.py

…

test_gemm.py

…

test_intel_amx_attention_backend_a.py

Split test_intel_amx_attention_backend.py to pass CI of timeout (#11370)

2025-10-15 19:22:32 -07:00

test_intel_amx_attention_backend_b.py

Split test_intel_amx_attention_backend.py to pass CI of timeout (#11370)

2025-10-15 19:22:32 -07:00

test_intel_amx_attention_backend_c.py

Split test_intel_amx_attention_backend.py to pass CI of timeout (#11370)

2025-10-15 19:22:32 -07:00

test_mla.py

…

test_moe.py

Fix FP8 block quantization when N or K is not multiples of 128 (#8648)

2025-08-01 15:57:19 -07:00

test_norm.py

…

test_qkv_proj_with_rope.py

…

test_rope.py

…

test_shared_expert.py

…

test_topk.py

[CPU][sgl-kernel] biased_grouped_topk: fix correction_bias dtype to float32 (#8212)

2025-08-04 18:28:31 -07:00

utils.py

[CPU] Add gelu_and_mul kernel in sgl-kernel and add ut (#9300)

2025-09-08 23:23:13 -07:00