onnxruntime
Quant tool: Use 2D scales and zp in default MatMulNBitsQuantizer
#26329
Merged

Quant tool: Use 2D scales and zp in default MatMulNBitsQuantizer #26329

jambayk merged 1 commit into main from jambayk/mnb-default
jambayk
jambayk use 2d scales and zp in default mnb quantizer
c2494143
jambayk jambayk requested a review from tianleiwu tianleiwu 337 days ago
jambayk jambayk changed the title Quant Tool: Use 2D scales and zp in default MatMulNBitsQuantizer Quant tool: Use 2D scales and zp in default MatMulNBitsQuantizer 337 days ago
tianleiwu
tianleiwu approved these changes on 2025-10-17
jambayk jambayk merged 6dbd41b5 into main 337 days ago
jambayk jambayk deleted the jambayk/mnb-default branch 337 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone