Sam 922756aaa1 [FIX] trtllm-moe-fp4-renorm for Qwen series models (#14350)

2025-12-04 12:52:21 -08:00

..

ep_moe

[NPU][1/N] NPU basic functions refactor and new modelslim quant type (#13359)

2025-12-04 16:15:31 +08:00

fused_moe_triton

[FIX] trtllm-moe-fp4-renorm for Qwen series models (#14350)

2025-12-04 12:52:21 -08:00

moe_runner

Single Batch Overlap for MoE Models (#9660)

2025-12-03 10:07:42 -08:00

token_dispatcher

Single Batch Overlap for MoE Models (#9660)

2025-12-03 10:07:42 -08:00

__init__.py

…

cutlass_moe_params.py

…

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

[Perf] Optimize DeepSeek-R1 w4afp8 glue kernels (#10027)

2025-11-24 11:05:38 -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

…

router.py

…

topk.py

[NPU][1/N] NPU basic functions refactor and new modelslim quant type (#13359)

2025-12-04 16:15:31 +08:00

utils.py

[Ascend] qwen optimization (#12078)

2025-11-25 19:44:24 +08:00