Skip to content

Conversation

Duyi-Wang
Copy link
Contributor

No description provided.

@Duyi-Wang Duyi-Wang requested a review from pujiang2018 March 6, 2024 07:08
CHANGELOG.md Outdated
v1.4.0 - Support fully BF16 inference deployment of Llama series and add serving supports.

## Functionality
- Introduce pure BF16 support in Llama series models, now can use fully BF16 data type to deployment Llama models.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Since BF16 previously already supported (though not the fully support), suggest to modify it like:
Introduce fully BF16 support in Llama series models to better use AMX

@Duyi-Wang Duyi-Wang merged commit 7587560 into intel:main Mar 8, 2024
@Duyi-Wang Duyi-Wang deleted the release_1.4.0 branch March 29, 2024 07:19
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants