Michael Goin 09e4576f65 [Kernel] Add non-gated support for NVFP4 CUTLASS MoE (#37320) ...

Signed-off-by: mgoin <mgoin64@gmail.com>

2026-03-17 18:12:04 -04:00

..

moe-refactor

[Kernel] Add non-gated support for NVFP4 CUTLASS MoE (#37320)

2026-03-17 18:12:04 -04:00

moe-refactor-dp-ep

…

DeepSeek-R1-DP.yaml

…

DeepSeek-R1-TP.yaml

…

DeepSeek-V2-Lite-Instruct-FP8.yaml

…

DeepSeek-V3.2-DP.yaml

…

DeepSeek-V3.2-TP.yaml

…

Llama-3-8B-Instruct-nonuniform-CT.yaml

…

Llama-3.2-1B-Instruct-INT8-CT.yaml

…

models-blackwell.txt

…

models-h200.txt

…

models-mi355.txt

…

models-small.txt

…

Qwen1.5-MoE-W4A16-CT.yaml

…

Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml

…

Qwen3-0.6B-FP8.yaml

…

Qwen3-30B-A3B-MXFP4A16.yaml

…

Qwen3-30B-A3B-NVFP4.yaml

…

Qwen3-Next-80B-A3B-NVFP4-EP2.yaml

…

Qwen3-Next-FP8-EP2_MI355.yaml

…

Qwen3-Next-FP8-EP2.yaml

…