Cheng Wan 2f8ba6fe82 [Fix] MoE: fix w8a8_fp8 MoE and add tests to cover this code path (#10429)

2025-09-14 17:34:28 -07:00

..

test_awq_dequant.py

…

test_awq.py

…

test_block_int8.py

[6/N] MoE Refactor: Cleanup MoE-related configs (#8849)

2025-08-14 21:14:53 -07:00

test_fp8_kernel.py

…

test_fp8_kvcache.py

…

test_int8_kernel.py

[6/N] MoE Refactor: Cleanup MoE-related configs (#8849)

2025-08-14 21:14:53 -07:00

test_triton_scaled_mm.py

Support Triton FP8 Gemm can handle hidden_dim not divisible by 16 (#9093)

2025-08-12 21:21:55 -07:00

test_w4a8_deepseek_v3.py

[CI] add deepseek w4a8 test on h20 ci (#7758)

2025-08-16 01:54:13 -07:00

test_w8a8_quantization.py

[Fix] MoE: fix w8a8_fp8 MoE and add tests to cover this code path (#10429)

2025-09-14 17:34:28 -07:00