Skip to content

Fix DQ→MatMulNBits fusion for FP16 models on CPU EP#27640

Merged
jambayk merged 3 commits into
mainfrom
jambayk/qdq-mnb-arm
Mar 14, 2026
Merged

Fix DQ→MatMulNBits fusion for FP16 models on CPU EP#27640
jambayk merged 3 commits into
mainfrom
jambayk/qdq-mnb-arm

update dqmatmul rule to allow fp16 matmul on cpu ep

3e64aa2
Select commit
Loading
Failed to load commit list.
Azure Pipelines / Linux_TRT_Minimal_CUDA_Test_CI succeeded Mar 14, 2026 in 42m 49s

Build #20260313.32 succeeded