Michael Goin 8efd508204 [Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)

2026-05-13 16:58:32 -04:00

..

configs

Add tuned triton fused_moe configs on H100 for gpt-oss (#39904)

2026-04-28 03:38:48 -07:00

experts

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

oracle

[Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)

2026-05-13 16:58:32 -04:00

prepare_finalize

[MoE Refactor] Add sequence parallel tests to test_moe_layer.py (#41299)

2026-05-12 21:52:19 -04:00

router

[MoE Refactor] EPLB refactoring for FusedMoE (#41055)

2026-05-12 14:16:31 -04:00

runner

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

__init__.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

activation.py

[Model] Fix Gemma4 MoE activation mismatch (#41574)

2026-05-05 04:34:11 +00:00

all2all_utils.py

[DSV4] Add BF16 and MXFP8 A2A support for flashinfer a2a one sided (#40960)

2026-04-30 15:33:12 -07:00

config.py

[Bugfix] Fix FlashInfer CUTLASS MXFP4-MXFP8 MoE by restoring swizzled scale (#42089)

2026-05-08 15:59:06 -07:00

cpu_fused_moe.py

[CPU] Bump up to the latest CPU kernels (#41924)

2026-05-07 05:45:59 -07:00

deep_gemm_utils.py

Fix DeepGEMM ep_scatter output address overflow (#39213)

2026-05-05 18:56:56 +00:00

expert_map_manager.py

[MoE Refactor] Move expert map related code into ExpertMapManager class (#41046)

2026-05-12 09:18:27 -04:00

fused_moe_method_base.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

fused_moe_modular_method.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

fused_moe.py

[MoE] Move various experts classes to fused_moe/experts/ (#41979)

2026-05-11 07:54:33 +08:00

layer.py

[MoE Refactor] EPLB refactoring for FusedMoE (#41055)

2026-05-12 14:16:31 -04:00

modular_kernel.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

moe_align_block_size.py

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

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

moe_fused_mul_sum.py

[Quantization] add humming quantization kernel (#34556)

2026-04-24 09:29:44 -04:00

moe_permute_unpermute.py

[Refactor] Remove align block size logic in moe_permute (#33449)

2026-02-06 10:57:06 -08:00

routed_experts_capturer.py

[Core] Replace routing replay with device cache and async D2H pipeline (#39917)

2026-05-07 11:24:56 -07:00

topk_weight_and_reduce.py

Eliminate redundant MoE buffer copies in AITER fused experts (without dependency on AITER changes) (#41713)

2026-05-07 03:46:40 -07:00

unquantized_fused_moe_method.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

utils.py

[Bugfix] Fix FlashInfer CUTLASS MXFP4-MXFP8 MoE by restoring swizzled scale (#42089)

2026-05-08 15:59:06 -07:00