[Feat][Helm] Add vllmConfig.revision for HuggingFace model version pinning#961
Merged
ruizhang0101 merged 4 commits intoJun 25, 2026
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces support for pinning Hugging Face model versions using a new revision configuration parameter in the Helm chart. It updates the documentation, values schema, templates, and adds corresponding unit tests. However, the unit tests in helm/tests/ray-cluster_test.yaml contain incorrect document indices (using index 1 instead of 2) when asserting the contents of the vllm-entrypoint.sh script inside the rendered ConfigMap, which will cause the tests to target the wrong document.
Collaborator
|
Could you fix the pre-commit issue when you have time? |
robertobarreda
force-pushed
the
feat/vllmconfig-revision-pinning
branch
2 times, most recently
from
3f8cf23 to
d4fdb98
Compare
Contributor
Author
Fixed, although I don't see them executing again. |
robertobarreda
force-pushed
the
feat/vllmconfig-revision-pinning
branch
from
d4fdb98 to
942f2fb
Compare
Contributor
Author
|
@ruizhang0101 it looks like the functionality test timeout for some reason |
ruizhang0101
requested changes
Jun 22, 2026
ruizhang0101
left a comment
ruizhang0101
left a comment
Collaborator
There was a problem hiding this comment.
Hi, could you put this in the model spec instead of vllm config?
modelSpec:
- name: "llama3"
repository: "vllm/vllm-openai"
tag: "latest"
modelURL: "meta-llama/Llama-3.1-8B-Instruct"
modelRevision: <COMMIT_HASH>
robertobarreda
force-pushed
the
feat/vllmconfig-revision-pinning
branch
from
942f2fb to
c766fd8
Compare
…nning Add a `revision` field to `vllmConfig` that maps to vLLM's `--revision` flag, allowing operators to pin deployed models to a specific HuggingFace Hub branch, tag, or commit hash. Without this, vLLM always pulls the latest commit on the default branch, which can silently change model behaviour across re-deploys. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> Signed-off-by: Roberto Barreda <roberto.barreda@midokura.com>
Signed-off-by: Roberto Barreda <roberto.barreda@midokura.com>
robertobarreda
force-pushed
the
feat/vllmconfig-revision-pinning
branch
2 times, most recently
from
4c15218 to
a827843
Compare
Move revision pinning from vllmConfig.revision to modelRevision at the model spec level, making it a first-class field on each model entry. - Add modelRevision to modelSpec defaults and schema - Update deployment-vllm-multi and ray-cluster templates to read $modelSpec.modelRevision - Update tests to use modelRevision instead of vllmConfig.revision - Update docs to reference modelRevision - Add llama3 example entry to values-01 with pinned revision modelRevision for meta-llama/Llama-3.1-8B-Instruct obtained via: curl -s https://huggingface.co/api/models/meta-llama/Llama-3.1-8B-Instruct | yq -p json '.sha' Signed-off-by: Roberto Barreda <roberto.barreda@midokura.com>
robertobarreda
force-pushed
the
feat/vllmconfig-revision-pinning
branch
from
a827843 to
e7665f3
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add a
modelRevisionfield to the model spec that maps to vLLM's--revisionflag, allowing operators to pin deployed models to a specific HuggingFace Hub branch, tag, or commit hash.Without this, vLLM always pulls the latest commit on the default branch, which can silently change model behaviour across re-deploys.
modelRevisionis a first-class field on each model spec entry (not nested undervllmConfig), making it discoverable and consistent with other model-level fields.Changes:
helm/values.yaml+values.schema.json: addmodelRevisionfield to model spec (empty string default = no pinning), remove oldvllmConfig.revisionhelm/templates/deployment-vllm-multi.yaml: emit--revision <value>when$modelSpec.modelRevisionis sethelm/templates/ray-cluster.yaml: same for Ray cluster deploymentshelm/tests/: positive and negative unit tests for both deployment pathsdocs/source/deployment/helm.rst: documentmodelRevisioninstead ofrevision.github/values-01-2pods-minimal-example.yaml: add llama3 example with pinnedmodelRevisionmodelRevision for
meta-llama/Llama-3.1-8B-Instructobtained via:curl -s https://huggingface.co/api/models/meta-llama/Llama-3.1-8B-Instruct | yq -p json '.sha'