text-generation-inference
Do not convert weight scale to e4m3fnuz on CUDA
#2917
Merged
Overview
Commits
1
Changes
View On GitHub

Do not convert weight scale to e4m3fnuz on CUDA #2917

Narsil merged 1 commit into main from bugfix/cuda-no-e4m3fnuz
danieldk
danieldk Do not convert weight scale to e4m3fnuz on CUDA
f951a8b4
Narsil
Narsil approved these changes on 2025-01-16
Narsil Narsil merged 5f78ec32 into main 338 days ago
Narsil Narsil deleted the bugfix/cuda-no-e4m3fnuz branch 338 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum