Chunyuan WU 08f8f49016 [CPU][sgl-kernel] biased_grouped_topk: fix correction_bias dtype to float32 (#8212) ...

Co-authored-by: jianan-gu <jianan.gu@intel.com>
Co-authored-by: YanbingJiang <yanbing.jiang@intel.com>

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

..

test_activation.py

Update seed in CPU UTs to avoid flaky failure with single test (#7544)

2025-06-25 21:25:50 -07:00

test_binding.py

[CPU] add c++ kernel to bind CPU cores and memory node (#7524)

2025-06-29 19:45:25 -07:00

test_decode.py

Support non-contiguous query input for extend/decode attention (#7462)

2025-07-02 19:59:45 -07:00

test_extend.py

Support non-contiguous query input for extend/decode attention (#7462)

2025-07-02 19:59:45 -07:00

test_gemm.py

Update seed in CPU UTs to avoid flaky failure with single test (#7544)

2025-06-25 21:25:50 -07:00

test_mla.py

Update seed in CPU UTs to avoid flaky failure with single test (#7544)

2025-06-25 21:25:50 -07:00

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

Update seed in CPU UTs to avoid flaky failure with single test (#7544)

2025-06-25 21:25:50 -07:00

test_qkv_proj_with_rope.py

Update seed in CPU UTs to avoid flaky failure with single test (#7544)

2025-06-25 21:25:50 -07:00

test_rope.py

Update seed in CPU UTs to avoid flaky failure with single test (#7544)

2025-06-25 21:25:50 -07:00

test_shared_expert.py

Update seed in CPU UTs to avoid flaky failure with single test (#7544)

2025-06-25 21:25:50 -07:00

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

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

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