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

Dynamic block device volume size and entry point changes #152

Merged

Conversation

estohlmann
Copy link
Member

A request was made to support block device volume size being configurable, added optional API param to accomplish this.

For the TGI entrypoint:

  • Added number of shards and CUDA settings (increase model memory footprint by distributing model across available GPU's)
  • Fixed quantization not being applied by text-generation-launcher (variable being set but not applied by text-generation-launcher)

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

bedanley
bedanley previously approved these changes Oct 18, 2024
dustins
dustins previously approved these changes Oct 21, 2024
@estohlmann estohlmann merged commit 8a6f79f into develop Oct 21, 2024
4 checks passed
@estohlmann estohlmann deleted the feature/block-device-volume-size-and-entry-point-changes branch October 21, 2024 17:02
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