fix: Update Vertex AI endpoint to use HTTP restriction config - #8680
Merged
pskiran1 merged 14 commits intoMar 7, 2026
Merged
Conversation
pskiran1
changed the title
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes the Vertex AI endpoint so that it properly respects the HTTP restriction configuration (--http-restricted-api and --http-max-input-size). Previously, Vertex AI was constructing its HTTPAPIServer base class with hardcoded defaults for these values; now the values are passed through from the user-configured HTTP settings.
Changes:
- Updated
VertexAiAPIServer::Create()andVertexAiAPIServerconstructor to acceptmax_input_sizeandrestricted_apisparameters. - Updated
StartVertexAiService()inmain.ccto readhttp_max_input_size_andhttp_restricted_apis_from global params (when HTTP is enabled) and pass them toVertexAiAPIServer::Create(). - Added a new test section in
qa/L0_vertex_ai/test.shthat verifies restriction enforcement on the Vertex AI redirect mechanism.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
src/vertex_ai_server.h |
Added max_input_size and restricted_apis parameters to Create() and the private constructor. Updated copyright to 2026. |
src/vertex_ai_server.cc |
Updated constructor and Create() implementation to accept and forward the new parameters to the base class. Updated copyright to 2026. |
src/main.cc |
Added code to read HTTP config for max_input_size and restricted_apis (guarded by TRITON_ENABLE_HTTP) before calling VertexAiAPIServer::Create(). Updated copyright to 2026. |
qa/L0_vertex_ai/test.sh |
Added setup for a restricted_single_model Python model repository and a comprehensive test section verifying that restricted APIs are correctly blocked/allowed on the Vertex AI redirect mechanism. Updated copyright to 2026. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
pskiran1
changed the title
…rver-vertex-ai-integration-access
Contributor
|
LGTM |
mattwittwer
previously approved these changes
Mar 4, 2026
…rver-vertex-ai-integration-access
yinggeh
reviewed
Mar 5, 2026
yinggeh
reviewed
Mar 5, 2026
yinggeh
reviewed
Mar 5, 2026
…rver-vertex-ai-integration-access
yinggeh
previously approved these changes
Mar 6, 2026
Co-authored-by: Yingge He <157551214+yinggeh@users.noreply.github.com>
yinggeh
approved these changes
Mar 6, 2026
whoisj
approved these changes
Mar 6, 2026
20 tasks
pskiran1
deleted the
spolisetty/tri-669-psirt-triton-inference-server-vertex-ai-integration-access
branch
March 7, 2026 12:09
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 does the PR do?
This PR fixes the Vertex AI endpoint so that it properly respects the HTTP restriction configuration (
--http-restricted-apiand--http-max-input-size). Previously, Vertex AI was constructing itsHTTPAPIServerbase class with hardcoded defaults for these values; now the values are passed through from the user-configured HTTP settings.Changes:
VertexAiAPIServer::Create()andVertexAiAPIServerconstructor to acceptmax_input_sizeandrestricted_apisparameters.StartVertexAiService()inmain.ccto readhttp_max_input_size_andhttp_restricted_apis_from global params (when HTTP is enabled) and pass them toVertexAiAPIServer::Create().qa/L0_vertex_ai/test.shthat verifies restriction enforcement on the Vertex AI redirect mechanism.Checklist
<commit_type>: <Title>Commit Type:
Check the conventional commit type
box here and add the label to the github PR.
Related PRs:
Where should the reviewer start?
Test plan:
Caveats:
Background
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)