4 people 5ed15f42b9 Fix the E8M0 scale computation in the MXFP4 (W4A4) MOE CUTLASS kernel (#43557) ...

Signed-off-by: Xin He <xin3.he@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

2026-06-15 06:04:54 -07:00

..

modular_kernel_tools

[Bugfix] Fix broken profile_modular_kernel.py (#43300)

2026-06-11 12:17:23 +01:00

__init__.py

[Kernel] DeepEP dispatch-combine kernel integration (#18434)

2025-06-03 12:30:02 -07:00

conftest.py

[MoE Refactor][Test] FusedMoE layer test (#24675)

2026-04-06 17:17:23 +00:00

parallel_utils.py

[WideEP] Integrate DeepEP v2 (#41183)

2026-06-08 18:07:29 -07:00

test_batched_deepgemm.py

[MoE] Remove inplace fused experts mechanism (#43727)

2026-05-27 20:00:19 -07:00

test_batched_moe.py

[MoE Refactor] Move remaining experts classes to experts directory (#42334)

2026-05-12 09:19:46 -04:00

test_block_fp8.py

[MoE] Remove inplace fused experts mechanism (#43727)

2026-05-27 20:00:19 -07:00

test_block_int8.py

[Misc] Make SchedulerConfig.max_model_len init-only (#28733)

2025-11-15 01:59:31 -08:00

test_count_expert_num_tokens.py

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

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

test_cpu_fused_moe.py

[Kernel][MoE] Add GELU_TANH to CPU, CUTLASS, and WNA16 MoE backends (#42027)

2026-06-02 17:12:08 -04:00

test_cpu_int4_moe.py

[MoE Refactor] W4a8 int8 oracle (#42789)

2026-05-26 11:15:42 -04:00

test_cpu_quant_fused_moe.py

[CPU] Support CPU W4A16 INT4 MoE (#43409)

2026-06-12 07:12:37 +00:00

test_cutedsl_moe.py

[CI/Build] Bump flashinfer to v0.6.11.post2 (#41711)

2026-05-16 14:55:12 -07:00

test_cutlass_moe.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

test_cutlass_mxfp8_grouped_mm.py

[Kernel] Integrate SM100 MXFP8 blockscaled grouped MM and quant kernels (#34448)

2026-03-01 23:31:19 -08:00

test_deepep_deepgemm_moe.py

use split_group for pytorch process group creation (#41980)

2026-06-04 14:36:07 -04:00

test_deepep_moe.py

[ROCm][CI] fix fp8 support for test_deepep_moe (#45302)

2026-06-12 00:16:14 -05:00

test_deepep_v2_moe.py

[WideEP] Integrate DeepEP v2 (#41183)

2026-06-08 18:07:29 -07:00

test_deepgemm.py

[MoE] Remove inplace fused experts mechanism (#43727)

2026-05-27 20:00:19 -07:00

test_flashinfer_b12x_moe.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

test_flashinfer_moe.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

test_flashinfer.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

test_flydsl_moe.py

[ROCm][Perf] Enable W4A16 FlyDSL MoE (#44400)

2026-06-14 00:14:39 -07:00

test_fused_topk.py

test: add nan/inf clamp regression test for fused_topk_bias (#40553)

2026-04-22 00:46:53 +00:00

test_gemma4router.py

[FEAT] [Perf] [Gemma4] Fused Gemma4 Routing Function Triton (#39083)

2026-04-19 09:57:39 +00:00

test_gpt_oss_triton_kernels.py

[MoE] Move GPT OSS Triton kernel experts into fused_moe/experts/ (#39007)

2026-04-14 19:27:39 +00:00

test_grouped_topk.py

[Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning (#35007)

2026-03-23 18:31:14 -04:00

test_marlin_vs_trtllm_mxint4.py

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

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

test_modular_kernel_combinations.py

[MoE Refactor] Remove supports_expert_map (#43108)

2026-05-29 17:26:56 -04:00

test_modular_oai_triton_moe.py

[MoE] Remove inplace fused experts mechanism (#43727)

2026-05-27 20:00:19 -07:00

test_moe_align_block_size.py

[Bugfix] Fix expert_ids padding values in moe_align_block_size kernel (#35161)

2026-02-24 17:14:24 -08:00

test_moe_layer.py

Deprecations for v0.23 and v0.24 (#44992)

2026-06-11 14:35:38 +00:00

test_moe_permute_unpermute.py

[Perf] Optimize moe permute by pre-allocate buffer, 9~14% kernel performance improvement (#43014)

2026-05-28 06:18:26 -07:00

test_moe_weight_loading_padded.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

test_moe.py

Deprecations for v0.23 and v0.24 (#44992)

2026-06-11 14:35:38 +00:00

test_mxfp4_moe.py

Fix the E8M0 scale computation in the MXFP4 (W4A4) MOE CUTLASS kernel (#43557)

2026-06-15 06:04:54 -07:00

test_nvfp4_moe.py

[MoE] Remove inplace fused experts mechanism (#43727)

2026-05-27 20:00:19 -07:00

test_ocp_mx_moe.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

test_profile_modular_kernel.py

[Bugfix] Fix broken profile_modular_kernel.py (#43300)

2026-06-11 12:17:23 +01:00

test_rocm_aiter_topk.py

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

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

test_routing_simulator.py

[ROCm][CI] Fix AITER state leak in shared_fused_moe_routed_transform test (#38137)

2026-03-26 09:26:46 -07:00

test_routing.py

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

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

test_shared_fused_moe_routed_transform.py

[MoE Refactor] Remove SharedFusedMoE class (#35782)

2026-04-21 18:12:12 -04:00

test_silu_mul_fp8_quant_deep_gemm.py

[UX] Integrate DeepGEMM into vLLM wheel via CMake (#37980)

2026-04-08 18:56:32 -07:00

test_silu_mul_per_token_group_quant_fp8_colmajor.py

[Bugfix] Add swiglu limits to deepgemm fp8 methods (#41986)

2026-05-14 15:43:13 -07:00

test_topk_softplus_sqrt.py

[New Model][ROCm] Add AMD support for DeepSeek V4 (#40871)

2026-05-05 08:55:37 -07:00

test_triton_moe_no_act_mul.py

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

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

test_triton_moe_ptpc_fp8.py

[CI/Build] Only use supported types and features on ROCm in MoE kernel tests (#29149)

2025-11-21 20:34:33 -07:00

test_trtllm_nvfp4_moe.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

test_unquantized_backend_selection.py

Deprecations for v0.23 and v0.24 (#44992)

2026-06-11 14:35:38 +00:00

test_zero_expert_moe.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00

utils.py

[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)

2026-06-08 10:42:58 -04:00