[Fix] Override data parallel size for accelerator configs#611
Open
YouNeedCryDear wants to merge 1 commit into
Open
[Fix] Override data parallel size for accelerator configs#611YouNeedCryDear wants to merge 1 commit into
YouNeedCryDear wants to merge 1 commit into
Conversation
github-actions
Bot
added
inferenceservice
YouNeedCryDear
requested review from
CatherineSue,
beiguo218,
pallasathena92 and
slin1237
as code owners
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 this PR does
Adds accelerator-specific runtime argument overrides for data parallel size, covering
--dp-size,--dp,--data-parallel-size, and-dp. It also extends tensor and pipeline parallel overrides to handle-tpand-ppaliases.Why we need it
tensorParallelismOverride.dataParallelSizeis part of the ServingRuntime accelerator config API, but the runtime argument override logic only applied tensor and pipeline parallel sizes. As a result, accelerator configs could setdataParallelSizewithout changing the generated runtime command. This makes DP override behavior match TP and PP override behavior.Fixes # (not filed)
How to test
env GOCACHE=/private/tmp/ome-go-build-cache go test ./pkg/controller/v1beta1/inferenceservice/components -count=1Checklist
make testpasses locally