text-generation-inference
fix(server): fix fp8 weight loading
#2268
Merged

fix(server): fix fp8 weight loading #2268

OlivierDehaene merged 4 commits into main from fix/fp8_loading
OlivierDehaene
OlivierDehaene fix(server): fix fp8 weight loading
119918cc
OlivierDehaene fixed scales loading
74f1f6a7
OlivierDehaene update snap
0d68619e
OlivierDehaene OlivierDehaene force pushed from 44a2784c to 0d68619e 1 year ago
OlivierDehaene revert default dtype
6d8e3659
danieldk
danieldk approved these changes on 2024-07-22
OlivierDehaene OlivierDehaene merged 4844ff79 into main 1 year ago
OlivierDehaene OlivierDehaene deleted the fix/fp8_loading branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone