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

[HELM] Fixes - Add Args when running h2oGPT only #1610

Merged
merged 1 commit into from May 11, 2024

Conversation

EshamAaqib
Copy link
Member

No description provided.

@EshamAaqib EshamAaqib self-assigned this May 10, 2024
@EshamAaqib
Copy link
Member Author

EshamAaqib commented May 10, 2024

This is needed when running only h2oGPT without vLLM or TGI in cluster or deploying vLLM or TGI as separate Helm charts, Especially when depending completely on external LLM endpoints. When only h2oGPT is enabled it would fail to run since args are missing. This PR fixes this

Ex:

  • h2oGPTe Playground depends completely on external LLM endpoints so only h2oGPT is enabled, same case for HAMC Internal GenAI Envs
  • In HAMC we deploy the LLMs as separate Helm charts, and h2oGPT is deployed separately so only h2oGPT is enabled

Copy link
Contributor

@ozahavi ozahavi left a comment

Choose a reason for hiding this comment

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

LGTM

@EshamAaqib EshamAaqib merged commit 2745aef into main May 11, 2024
2 checks passed
@EshamAaqib EshamAaqib deleted the eshamaaqib/helm-arg-fix branch May 11, 2024 07:17
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.

None yet

4 participants