Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: improve star coder to support multi lora layers #2883

Merged
merged 5 commits into from
Jan 16, 2025

Conversation

drbh
Copy link
Collaborator

@drbh drbh commented Jan 7, 2025

This PR adds TensorParallelMultiAdapterLinear and TensorParallelAdapterRowLinear to flash_starcoder2_modeling.py to enable multi lora with the starcoder2 model

danieldk
danieldk previously approved these changes Jan 9, 2025
Copy link
Member

@danieldk danieldk left a comment

Choose a reason for hiding this comment

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

Looks good. Do we need a test for this?

Narsil
Narsil previously approved these changes Jan 15, 2025
@drbh drbh force-pushed the startcoder-support-multi-lora branch from 6d14cc3 to d611f0f Compare January 16, 2025 16:06
@drbh
Copy link
Collaborator Author

drbh commented Jan 16, 2025

optimistically merging since this PR was already approved and the only failing test appears to be flakey and unrelated.

will watch for regressions and rollback if needed

@drbh drbh merged commit 82f6ea1 into main Jan 16, 2025
13 of 14 checks passed
@drbh drbh deleted the startcoder-support-multi-lora branch January 16, 2025 21:23
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.

3 participants