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

add tgi bf16 setup on CPU k8s. #795

Merged
merged 2 commits into from
Sep 13, 2024
Merged

add tgi bf16 setup on CPU k8s. #795

merged 2 commits into from
Sep 13, 2024

Conversation

lkk12014402
Copy link
Collaborator

Description

  1. specific --dtype bfloat16 for tgi
  2. label node on k8s for selecting automatically

Issues

link this issue #330

Copy link

github-actions bot commented Sep 12, 2024

Dependency Review

✅ No vulnerabilities or license issues found.

Scanned Manifest Files

@letonghan
Copy link
Collaborator

letonghan commented Sep 12, 2024

Seems like there are some redundant parameters in UI-ConfigMap. @WenjiaoYue please help check with it~

@lianhao
Copy link
Collaborator

lianhao commented Sep 12, 2024

The redundancy in ui related config map is because the the manifests is automatically generated by helm chart, which supports all the chatqna/docsum/codegen/codetrans conversational/non-conversational UI. All the UIs are using different environment variables, that's why the redundancy.

Co-authored-by: Eero Tamminen <eero.t.tamminen@intel.com>
@lvliang-intel lvliang-intel merged commit ba17031 into main Sep 13, 2024
10 checks passed
@lvliang-intel lvliang-intel deleted the add_tgi_cpu_bf16 branch September 13, 2024 11:55
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.

7 participants