Divakar Verma d1e1fb4363 [Bugfix] Fix grouped_topk pytorch impl when num_experts can't be grouped properly (#29439) ...

Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>

2025-12-10 19:47:18 -08:00

..

configs

Add Mistral Large 3 and Ministral 3 (#29757)

2025-12-02 10:29:00 +00:00

__init__.py

[MoE][Refactor] Remove most arguments to FusedMoEMethodBase.apply (#29066)

2025-12-09 13:48:25 -08:00

all2all_utils.py

[Feat][Perf] Enable deepep-low-latency with round-robin expert placement. (#28449)

2025-11-19 13:46:24 +01:00

batched_deep_gemm_moe.py

[Performance][DeepGEMM] Estimate expected_m (#28694)

2025-11-15 13:52:14 +08:00

config.py

[Kernel]Support W4A8 Grouped GEMM on Hopper (#29691)

2025-12-08 19:29:06 -08:00

cpu_fused_moe.py

[fix][cpu] Use a SwigluOAI impl which supports interleaved gate-up wei (#29273)

2025-11-25 15:11:11 +08:00

cutlass_moe.py

[Kernel]Support W4A8 Grouped GEMM on Hopper (#29691)

2025-12-08 19:29:06 -08:00

deep_gemm_moe.py

[Perf] Deepgemm fused layout kernel for activations, 4.3% throughput improvement, 10.7% TTFT improvement. (#29546)

2025-12-07 20:31:14 +08:00

deep_gemm_utils.py

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

deepep_ht_prepare_finalize.py

[Bug] Fix DBO IMA issue for DeepEPHT (#27666)

2025-10-29 16:28:27 -04:00

deepep_ll_prepare_finalize.py

[MoE] CuteDSL MoE with Nvfp4 DeepEP dispatch (#27141)

2025-11-30 16:05:32 -08:00

flashinfer_cutedsl_moe.py

[MoE] CuteDSL MoE with Nvfp4 DeepEP dispatch (#27141)

2025-11-30 16:05:32 -08:00

flashinfer_cutlass_moe.py

Feature: Support Relu2 in FusedMoE fp8 cutlass path (#27261)

2025-11-16 13:39:44 -05:00

flashinfer_cutlass_prepare_finalize.py

[Kernels] Enable FlashInfer FP8 Blockscale on SM90 (for TEP DSR1) (#27134)

2025-11-14 08:02:44 -08:00

flashinfer_trtllm_moe.py

[Performance] Support FP8 flashinfer TRTLLM MOE on Qwen3 and Qwen-3next (#27492)

2025-11-10 12:34:57 -05:00

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

[Kernel][MoE] optimize moe_align_block_size (#29642)

2025-12-07 01:58:47 -08:00

fused_moe_method_base.py

[MoE][Refactor] Remove most arguments to FusedMoEMethodBase.apply (#29066)

2025-12-09 13:48:25 -08:00

fused_moe_modular_method.py

[MoE][Refactor] Remove most arguments to FusedMoEMethodBase.apply (#29066)

2025-12-09 13:48:25 -08:00

fused_moe.py

[Bugfix]: Fix glm46 awq marlin moe wna16 compatibility (#30210)

2025-12-09 12:20:21 +00:00

gpt_oss_triton_kernels_moe.py

[LoRA] Support FusedMoE LoRA Triton kernel for mxfp4 (#29708)

2025-11-30 10:37:25 +08:00

layer.py

[Bugfix] Fix grouped_topk pytorch impl when num_experts can't be grouped properly (#29439)

2025-12-10 19:47:18 -08:00

modular_kernel.py

[Kernel]Support W4A8 Grouped GEMM on Hopper (#29691)

2025-12-08 19:29:06 -08:00

moe_align_block_size.py

[Kernel][MoE] optimize moe_align_block_size (#29642)

2025-12-07 01:58:47 -08:00

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

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

prepare_finalize.py

[Feature] Shared Experts Overlap with FI deepgemm swap kernel, 2.2% throughput improvement and 3.6% TTFT improvement (#28879)

2025-11-20 18:41:49 -07:00

rocm_aiter_fused_moe.py

[ROCm][MXFP4] Infer w4a4 quant method in rocm aiter fused moe (#29775)

2025-12-05 11:01:16 +00:00

routing_simulator.py

[Bugfix] Fix MoE Routing Simulation (#28002)

2025-11-03 22:26:49 +00:00

shared_fused_moe.py

[Bugfix] fix IMA issue in certain cases of the moe marlin kernel (#28619)

2025-11-26 19:02:21 -08:00

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

[BugFix][Performance] Restore flashinfer autotuning for all scenarios (#27904)

2025-11-04 15:56:21 +08:00

unquantized_fused_moe_method.py

[MoE][Refactor] Remove most arguments to FusedMoEMethodBase.apply (#29066)

2025-12-09 13:48:25 -08:00

utils.py

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00