fix: Remove pip3 install tritonclient[all] from L0_infer install_and_test.sh#8818
Open
yinggeh wants to merge 3 commits into
Open
fix: Remove pip3 install tritonclient[all] from L0_infer install_and_test.sh#8818yinggeh wants to merge 3 commits into
yinggeh wants to merge 3 commits into
Conversation
…test.sh The public PyPI tritonclient wheel lacks ml_dtypes support, which breaks L0_infer on the compose/cpu-only images. Drop the pip install so the in-container client (built with ml_dtypes, supplied via the SDK image) is used instead.
Add an optional "sdk" value to --image so the generated inference Dockerfile copies and installs the tritonclient build carried by the specified SDK image. The behavior is opt-in and leaves images that do not pass --image=sdk unchanged.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 does the PR do?
L0_infercompose/cpu-only jobs runqa/L0_infer/install_and_test.sh, which didpip3 install tritonclient[all]from public PyPI. That public wheel lacksml_dtypessupport and overwrites the in-container client, breaking the tests until the next public client release. This PR removes thatpip3 installso the in-containertritonclient(built withml_dtypes, supplied via the SDK image) is used instead.Commit Type:
Related PRs:
py3-sdk-manifestinto the sevenL0_inferjobs so the SDK client is available (dl/dgx/tritonserveryinggeh/tri-1180-add-py3-sdk-manifest-as-dependency).Where should the reviewer start?
qa/L0_infer/install_and_test.shTest plan:
L0_infercompose/cpu-only jobs with the matching tritonserver branch and confirm they pass (noml_dtypesimport error).Caveats:
py3-sdk-manifestdependency) so the SDK client image is present.Background
The public
tritonclient[all]wheel trailsmainand omitsml_dtypes, so installing it inside the test container regressedL0_infer.Related Issues: