bnellnmandGitHub f9c069c85e Modularize fused experts and integrate PPLX kernels (#15956)

2025-05-14 13:11:54 -07:00

..

test_batched_moe.py

Modularize fused experts and integrate PPLX kernels (#15956)

2025-05-14 13:11:54 -07:00

test_cutlass_moe.py

Modularize fused experts and integrate PPLX kernels (#15956)

2025-05-14 13:11:54 -07:00

test_moe_permute_unpermute.py

permute/unpermute kernel for moe optimization (#14568)

2025-05-02 11:31:55 -07:00

test_moe.py

Modularize fused experts and integrate PPLX kernels (#15956)

2025-05-14 13:11:54 -07:00

test_nvfp4_moe.py

[Hardware/NVIDIA/Kernel] Enable nvidia/DeepSeek-R1-FP4 Model (#16362)

2025-05-09 16:24:41 -07:00

test_pplx_moe.py

Modularize fused experts and integrate PPLX kernels (#15956)

2025-05-14 13:11:54 -07:00

test_rocm_aiter_topk.py

[FEAT] [ROCm] [V1]: Add AITER biased group topk for DeepSeekV3 (#17955)

2025-05-13 22:03:47 -07:00

test_triton_moe_ptpc_fp8.py

Modularize fused experts and integrate PPLX kernels (#15956)

2025-05-14 13:11:54 -07:00