Skip to content

Route fp16 HQNBIT_CompInt8 (4-bit and 8-bit) through fp32 MLAS path in MatMulNBits#27820

Merged
jambayk merged 5 commits into
mainfrom
jambayk/mnb-4-16
Mar 25, 2026
Merged

Route fp16 HQNBIT_CompInt8 (4-bit and 8-bit) through fp32 MLAS path in MatMulNBits#27820
jambayk merged 5 commits into
mainfrom
jambayk/mnb-4-16

Address review: ORT_ENFORCE for scales, move SQNBIT check to GetCompu…

138318a
Select commit
Loading
Failed to load commit list.
Azure Pipelines / Win_TRT_Minimal_CUDA_Test_CI succeeded Mar 25, 2026 in 35m 34s

Build #20260324.60 succeeded