vllm/moe at ce58fdc1c366b0257c2b2d8310b14d4ea8f8dd30 - vllm

mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 03:35:17 +08:00

History

[Perf][DeepSeek] Add sigmoid+bias fusion to fused_grouped_topk from TRTLLM (#28124 )

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

2025-11-07 18:20:55 -08:00

marlin_moe_wna16

Convert formatting to use ruff instead of yapf + isort (#26247 )

2025-10-05 07:06:22 -07:00

permute_unpermute_kernels

…

dynamic_4bit_int_moe_cpu.cpp

[CPU]Improve dynamic 4bit moe performance (#27240 )

2025-11-04 06:33:23 +00:00

grouped_topk_kernels.cu

[Perf][DeepSeek] Add sigmoid+bias fusion to fused_grouped_topk from TRTLLM (#28124 )

2025-11-07 18:20:55 -08:00

moe_align_sum_kernels.cu

[GPTOSS][DP/EP][Marlin] Enable GPTOSS Batched DP/EP using Marlin kernels (#25997 )

2025-10-16 12:53:11 -07:00

moe_lora_align_sum_kernels.cu

Early exit for MoE LoRA kernels (#27131 )

2025-11-03 20:22:17 +08:00

moe_ops.h

[Perf][DeepSeek] Add sigmoid+bias fusion to fused_grouped_topk from TRTLLM (#28124 )

2025-11-07 18:20:55 -08:00

moe_permute_unpermute_op.cu

…

moe_wna16_utils.h

…

moe_wna16.cu

…

topk_softmax_kernels.cu

[Kernel][Performance] Fuse float cast and renormalize to topk softmax kernel (#26717 )

2025-10-17 07:30:35 +00:00

torch_bindings.cpp

[Perf][DeepSeek] Add sigmoid+bias fusion to fused_grouped_topk from TRTLLM (#28124 )

2025-11-07 18:20:55 -08:00