hzh0425 5c08a36cbf [Fix] ensure DeepGEMM is only enabled for FP8_W8A8 models (#8110)

2025-07-16 21:33:29 -07:00

..

ep_moe

[Fix] ensure DeepGEMM is only enabled for FP8_W8A8 models (#8110)

2025-07-16 21:33:29 -07:00

fused_moe_triton

[1/n] chore: decouple quantization implementation from vLLM dependency (#7992)

2025-07-16 15:56:26 -07:00

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

Add a CUDA kernel for fusing mapping and weighted sum for MoE. (#6916)

2025-06-07 15:24:39 -07:00

cutlass_w4a8_moe.py

feat: support DeepSeek-R1-W4AFP8 model with ep-moe mode (#7762)

2025-07-07 14:47:21 -07:00

fused_moe_native.py

[CPU] [BF16] Call fused_experts_cpu, weight_packed_linear and bmm_cpu kernel in DeepSeek model (#6641)

2025-06-25 01:43:33 -07:00

router.py

Improve streaming, log_level, memory report, weight loading, and benchmark script (#7632)

2025-06-29 23:16:19 -07:00

topk.py

[feature]Ascend quantization support (#7791)

2025-07-10 09:17:37 -07:00