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

Added configs for Neon VLLM service #79

Merged
merged 4 commits into from
Nov 1, 2024
Merged

Added configs for Neon VLLM service #79

merged 4 commits into from
Nov 1, 2024

Conversation

NeonKirill
Copy link
Contributor

Description

Added configuration to deploy Neon VLLM service via Diana Helm

@NeonKirill NeonKirill requested review from NeonDaniel and a team October 28, 2024 17:14
@NeonKirill NeonKirill self-assigned this Oct 28, 2024
Copy link
Member

@NeonDaniel NeonDaniel left a comment

Choose a reason for hiding this comment

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

Left a couple comments based on reading through changes.

  • I will address the chart version note and update Helm charts
  • After updating the chart version, I will test this by generating new charts and deploying to the alpha namespace and leave another review here

neon_diana_utils/configuration.py Show resolved Hide resolved
neon_diana_utils/helm_charts/mq/neon-llm-vllm/Chart.yaml Outdated Show resolved Hide resolved
Copy link
Member

@NeonDaniel NeonDaniel left a comment

Choose a reason for hiding this comment

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

Tested by rebuilding the alpha deployment. There is an outstanding issue there with Klat deployment config, but that is not related to these changes

@NeonDaniel NeonDaniel merged commit e3ec4e0 into dev Nov 1, 2024
5 checks passed
@NeonDaniel NeonDaniel deleted the support_for_vllm branch November 1, 2024 18:38
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