vLLM/vllm/model_executor/layers/fused_moe at 5beacce2eae2cb36e44498e2ea80b2d3ee34fe61 - vLLM

[Kernel][Model] Tune fused_moe Triton configs for Qwen3-30B A3/A3B on H100 (FP8/BF16) (#26268 )

2025-10-20 07:48:01 -07:00

__init__.py

[torch.compile] Unwrap fused_marlin_moe custom op (#26739 )

2025-10-14 02:22:16 +00:00

batched_deep_gemm_moe.py

[Feature] Migrate DeepGEMM API from get_m_alignment_for_contiguous_layout to get_mk_alignment_for_contiguous_layout (#26935 )

2025-10-16 16:46:48 -04:00

batched_triton_or_deep_gemm_moe.py

[Feature] Migrate DeepGEMM API from get_m_alignment_for_contiguous_layout to get_mk_alignment_for_contiguous_layout (#26935 )

2025-10-16 16:46:48 -04:00

config.py

[Chore] Separate out optional dependency checks from vllm.utils (#27207 )

2025-10-22 10:44:21 -04:00

cpu_fused_moe.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

cutlass_moe.py

[Bug] Fix DeepSeek-V2.5-1210-FP8 issue (#27267 )

2025-10-22 11:00:10 -04:00

deep_gemm_moe.py

[Chore] Separate out optional dependency checks from vllm.utils (#27207 )

2025-10-22 10:44:21 -04:00

deep_gemm_utils.py

[Feature] Migrate DeepGEMM API from get_m_alignment_for_contiguous_layout to get_mk_alignment_for_contiguous_layout (#26935 )

2025-10-16 16:46:48 -04:00

deepep_ht_prepare_finalize.py

[Bug] Fix Assertion error DeepEP/csrc/kernels/intranode.cu:928: 'false and Unsupported type' (#26532 )

2025-10-13 18:26:37 -04:00

deepep_ll_prepare_finalize.py

[Misc] Rev DeepEP (#27122 )

2025-10-18 14:54:29 +08:00

flashinfer_cutlass_moe.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

flashinfer_cutlass_prepare_finalize.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

flashinfer_trtllm_moe.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908 )

2025-10-18 09:48:22 -07:00

fused_batched_moe.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

fused_marlin_moe.py

[Feature][Kernel]FusedMoE LoRA (#21229 )

2025-10-21 03:01:37 +00:00

fused_moe.py

[Feature][Kernel]FusedMoE LoRA (#21229 )

2025-10-21 03:01:37 +00:00

gpt_oss_triton_kernels_moe.py

[Chore] Separate out optional dependency checks from vllm.utils (#27207 )

2025-10-22 10:44:21 -04:00

layer.py

[Chore] Separate out optional dependency checks from vllm.utils (#27207 )

2025-10-22 10:44:21 -04:00

modular_kernel.py

[Feature][Kernel]FusedMoE LoRA (#21229 )

2025-10-21 03:01:37 +00:00

moe_align_block_size.py

[GPTOSS][DP/EP][Marlin] Enable GPTOSS Batched DP/EP using Marlin kernels (#25997 )

2025-10-16 12:53:11 -07:00

moe_pallas.py

Convert formatting to use ruff instead of yapf + isort (#26247 )

2025-10-05 07:06:22 -07:00

moe_permute_unpermute.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

moe_torch_iterative.py

Convert formatting to use ruff instead of yapf + isort (#26247 )

2025-10-05 07:06:22 -07:00

pplx_prepare_finalize.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

prepare_finalize.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

rocm_aiter_fused_moe.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908 )

2025-10-18 09:48:22 -07:00

routing_simulator.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

shared_fused_moe.py

[Performance] Dual stream execution of "shared_experts" and "selected_experts" inside FusedMoE (#26440 )

2025-10-21 21:38:29 +00:00

topk_weight_and_reduce.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

triton_deep_gemm_moe.py

[Feature] Migrate DeepGEMM API from get_m_alignment_for_contiguous_layout to get_mk_alignment_for_contiguous_layout (#26935 )

2025-10-16 16:46:48 -04:00

trtllm_moe.py

[NVIDIA] [Perf] Update to leverage flashinfer trtllm FP4 MOE throughput kernel (#26714 )

2025-10-16 16:20:25 -07:00

utils.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908 )

2025-10-18 09:48:22 -07:00