feat(chart): allow extra args, init containers, and volumes for token…#2139
Open
dkhachyan wants to merge 1 commit into
Open
feat(chart): allow extra args, init containers, and volumes for token…#2139dkhachyan wants to merge 1 commit into
dkhachyan wants to merge 1 commit into
Conversation
Contributor
|
🚨 Unsigned commits detected! Please sign your commits. For instructions on how to set up GPG/SSH signing and verify your commits, please see GitHub Documentation. |
…izer The tokenizer render sidecar could not be customized beyond its args and volume mounts. Add extraArgs, initContainers, and volumes so deployments can prewarm the model cache and mount supporting storage. Signed-off-by: Denis Khachyan <khachyanda@gmail.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What type of PR is this?
/kind feature
What this PR does / why we need it:
The tokenizer render sidecar (
router.tokenizer.*) in the router Helm chartcould only be customized through its
argsandvolumeMounts. There was noway to append extra flags on top of the default args, run pod-level init
containers, or declare additional pod-level volumes.
This adds three fields to the tokenizer configuration:
router.tokenizer.extraArgs- args appended to thevllm-rendercontainerafter the default (or overridden) args.
router.tokenizer.initContainers- pod-level init containers, rendered onlywhen the tokenizer is enabled (e.g. to prewarm the model cache).
router.tokenizer.volumes- pod-level volumes rendered alongside thebuilt-in
model-cachevolume, so an init container and the sidecar canshare storage.
All three default to empty and render nothing when unset, so existing
deployments are unaffected.
config/charts/README.mddocuments the new fields.Which issue(s) this PR fixes:
Fixes #