vllm/model_executor/layers/quantization/modelopt.py · 6b7a81185d7e0f0fbad23d59db857eeafee688f7 · OpenDAS / vllm_cscc

Bugfix: Cutlass FP8 FusedMoE bad scaling factors (#27255) · 6b7a8118

amirkl94 authored Nov 05, 2025


Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

6b7a8118

modelopt.py 67.4 KB

Replace modelopt.py