周周周 95243f012c [Others] add PADDLE_ENFORCE (#5288)

2025-11-28 14:23:35 +08:00

..

moe_wna16_marlin_utils

…

deepgemm_preprocess.cu

…

ep_moe_expert_dispatch.cu

[Others] add PADDLE_ENFORCE (#5288)

2025-11-28 14:23:35 +08:00

fused_moe_helper.h

【New Feature】W4afp8 supports per group quantization (#4987)

2025-11-13 19:17:27 +08:00

fused_moe_imp_op.h

[BugFix] Fix zero workspace returned by CUB size query under CUDA Graph in MoE dispatch (#5087)

2025-11-20 20:00:29 +08:00

fused_moe_op.h

【New Feature】W4afp8 supports per group quantization (#4987)

2025-11-13 19:17:27 +08:00

fused_moe.cu

…

gptq_marlin_repack.cu

…

group_swiglu_with_masked.cu

…

group_swiglu_with_masked.h

…

moe_deepgemm_depermute.cu

…

moe_deepgemm_permute.cu

…

moe_dispatch.cu

[BugFix] Fix zero workspace returned by CUB size query under CUDA Graph in MoE dispatch (#5087)

2025-11-20 20:00:29 +08:00

moe_expert_ffn_wint2.cu

…

moe_fast_hardamard_impl_common.h

…

moe_fast_hardamard_impl.cuh

…

moe_fast_hardamard_kernel.cu

【Fix】fix deepep dispatch (#5036)

2025-11-17 10:34:01 +08:00

moe_fast_hardamard_kernel.h

…

moe_ffn.cu

【New Feature】W4afp8 supports per group quantization (#4987)

2025-11-13 19:17:27 +08:00

moe_reduce.cu

…

moe_redundant_topk_select.cu

…

moe_topk_select.cu

…

moe_wna16_marlin_gemm.cu

…

moe_wna16_marlin_gemm.h

…

swigluoai.cu

…

swigluoai.h

…

template_config.json

【New Feature】W4afp8 supports per group quantization (#4987)

2025-11-13 19:17:27 +08:00

tritonmoe_preprocess.cu

…

winx_unzip.cu

…