fix fp16 Qwen2 series model to DeepSpeed-FastGen #6028
fix Qwen2 serial model to DeepSpeed-FastGen
a9b82bc8
Merge branch 'master' into master
4e0b6fc7
tohtana
approved these changes
on 2024-08-21
tohtana
merged
e6fcc226
into master 1 year ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub