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

Set min/max replicas from annotation #8

Merged
merged 3 commits into from
Nov 1, 2023
Merged

Set min/max replicas from annotation #8

merged 3 commits into from
Nov 1, 2023

Conversation

nstogner
Copy link
Contributor

@nstogner nstogner commented Nov 1, 2023

Fixes #1

NOTE: Also changes the lingo-models annotation to the proper domain-prefix annotation: lingo.substratus.ai/models.

README.md Outdated
@@ -32,15 +32,15 @@ Deploy an embedding model:
```bash
helm install stapi-minilm-l6-v2 substratusai/stapi \
--set model=all-MiniLM-L6-v2 \
--set deploymentAnnotations.lingo-models=text-embedding-ada-002 \
--set deploymentAnnotations."lingo\.substratus\.ai/models"=text-embedding-ada-002 \
Copy link
Contributor

Choose a reason for hiding this comment

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

do we really need those \ ? it makes it a bit uggly to read.

Could we do this instead?

--set "deploymentAnnotations.lingo.substratus.ai/models=text-embedding-ada-002"

I am not sure you even need the double quotes

Copy link
Contributor

Choose a reason for hiding this comment

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

I can't get it to work without them either

Copy link
Contributor

Choose a reason for hiding this comment

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

reading values.yaml from bash heredoc seems best:

helm install mistral-7b-instruct substratusai/vllm -f - << EOF
model: mistralai/Mistral-7B-Instruct-v0.1
replicaCount: 0
deploymentAnnotations:
  lingo.substratus.ai/models: mistral-7b-instruct-v0.1
EOF

@samos123 samos123 merged commit 9938e06 into main Nov 1, 2023
1 check passed
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.

Configurable min/max replicas
2 participants