Hubert Lu d6d5c3fdea [AMD] Clean up vllm dependencies in moe_runner/triton.py (#11349) ...

Co-authored-by: HAI <hixiao@gmail.com>

2026-01-09 00:24:04 -08:00

..

ep_moe

[Refactor] Clean up custom op (#15995)

2026-01-01 21:41:56 +08:00

fused_moe_triton

MoE Refactor: Refactor fp8.py -> flashinfer_trllm.py (#15151)

2026-01-07 15:35:00 -08:00

moe_runner

[AMD] Clean up vllm dependencies in moe_runner/triton.py (#11349)

2026-01-09 00:24:04 -08:00

token_dispatcher

[Misc]Register and refactor some environs for dpsk-fp4 and DeepEp (#14538)

2025-12-06 12:29:16 -08:00

__init__.py

Add --speculative-moe-runner-backend server arg (#10183)

2025-11-04 00:20:56 -08:00

cutlass_moe_params.py

[CUTLASS-FP4-MOE] Introduce CutlassMoEParams class for easy initialization of Cutlass Grouped Gems Metadata (#6887)

2025-06-05 13:13:14 -07:00

cutlass_moe.py

[sgl-kernel][5/N]Support Expert Specialization Grouped GEMM (#12666)

2025-11-11 21:23:25 -08:00

cutlass_w4a8_moe.py

[JIT kernel] Apply jit per_tensor_quant_fp8 kernel (#15836)

2026-01-05 10:15:00 +08:00

flashinfer_cutedsl_moe.py

Replace [silu_and_mul_]scaled_fp4_group_quant by Flashinfer equivalent (#12376)

2025-11-13 00:26:00 -08:00

fused_moe_native.py

[11/N] MoE Refactor: Simplifying SBO Implementation with Dispatcher Hooks (#13327)

2025-11-21 01:11:37 -08:00

kt_ep_wrapper.py

Refactor KTransformers heterogeneous compute with unified GPU-quantization backend (#12834)

2025-11-09 21:06:32 -08:00

rocm_moe_utils.py

[Refactor] Clean up custom op (#15995)

2026-01-01 21:41:56 +08:00

routed_experts_capturer.py

[Feature] Enable return routed experts (#12162)

2025-12-21 15:16:43 +08:00

router.py

move more files under srt/utils (#11285)

2025-10-09 16:46:15 -07:00

topk.py

[Refactor] Rename CustomOp -> MultiPlatformOp (#16175)

2025-12-31 01:16:32 +08:00

utils.py

[NVIDIA] Fixes for NVFP4 all-gather with spec decoding (#15280)

2025-12-16 16:58:39 -08:00