[TRTLLM-8413][chore] resolve sampling defaults in OpenAI API backend #8121

ixlmar · 2025-10-02T14:20:49Z

Description

The OpenAI completions APIs default to non-greedy sampling. By constrast LLM (and SamplingParams) default to greedy sampling (and may change in the future). Therefore, the OpenAI API defaults need to be resolved within the OpenAI API implementation.

Test Coverage

PR Checklist

Please review the following before submitting your PR:

PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

Summary by CodeRabbit

Refactor
- Standardized request parameters for completions and chat: temperature and top_p now require numeric values; null is no longer accepted.
- Defaults remain 1.0 when these fields are omitted.
- Requests that previously sent null for these fields may now fail validation; update clients to provide numbers or omit to use defaults.

ixlmar · 2025-10-02T14:20:58Z

/bot run

tensorrt-cicd · 2025-10-02T14:26:48Z

PR_Github #20534 [ run ] triggered by Bot

coderabbitai · 2025-10-02T16:43:48Z

📝 Walkthrough

Walkthrough

Adjusted type annotations in tensorrt_llm/serve/openai_protocol.py: temperature and top_p fields in CompletionRequest and ChatCompletionRequest changed from Optional[float] to float, retaining default values.

Changes

Cohort / File(s)	Summary
OpenAI protocol request schema `tensorrt_llm/serve/openai_protocol.py`	Made temperature and top_p non-optional floats in CompletionRequest and ChatCompletionRequest; defaults unchanged (1.0).

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description Check	⚠️ Warning	The PR description includes the required Description and PR Checklist sections but leaves the Test Coverage section as a placeholder without listing any relevant tests, so it does not fully adhere to the template.	Please fill in the Test Coverage section by listing the specific test cases or suites that validate the changes to the OpenAI API defaults.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title Check	✅ Passed	The title clearly identifies the JIRA ticket, labels the change as a chore, and succinctly describes the main purpose of the PR, namely resolving sampling defaults in the OpenAI API backend, without extraneous detail.
Docstring Coverage	✅ Passed	No functions found in the changes. Docstring coverage check skipped.

✨ Finishing touches

📝 Generate Docstrings

🧪 Generate unit tests

Create PR with unit tests
Post copyable unit tests in a comment

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 293637e and aa97b54.

📒 Files selected for processing (1)

tensorrt_llm/serve/openai_protocol.py (2 hunks)

🧰 Additional context used

📓 Path-based instructions (3)

**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Use only spaces, no tabs; indent with 4 spaces.

Files:

tensorrt_llm/serve/openai_protocol.py

**/*.py

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.

Files:

tensorrt_llm/serve/openai_protocol.py

**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).

Files:

tensorrt_llm/serve/openai_protocol.py

🔇 Additional comments (2)

tensorrt_llm/serve/openai_protocol.py (2)

223-224: Enforce non-greedy sampling defaults
Changing temperature and top_p to non-optional float (default 1.0) aligns with OpenAI API behavior and no callers pass None.

513-514: Approve ChatCompletionRequest defaults
No instantiations pass None for temperature or top_p; change is safe.

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

tensorrt-cicd · 2025-10-02T18:39:10Z

PR_Github #20534 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15491 completed with status: 'FAILURE'

ixlmar · 2025-10-03T07:14:29Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-03T07:20:24Z

PR_Github #20572 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-03T10:46:20Z

PR_Github #20572 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15527 completed with status: 'FAILURE'

Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>

ixlmar · 2025-10-03T11:01:43Z

/bot run --only-multi-gpu-test --disable-fail-fast

tensorrt-cicd · 2025-10-03T11:06:58Z

PR_Github #20577 [ run ] triggered by Bot

ixlmar · 2025-10-03T13:26:06Z

/bot run

tensorrt-cicd · 2025-10-03T13:26:09Z

PR_Github #20577 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15532 (Partly Tested) completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

tensorrt-cicd · 2025-10-03T13:31:51Z

PR_Github #20584 [ run ] triggered by Bot

ixlmar · 2025-10-03T14:34:38Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-03T14:39:48Z

PR_Github #20590 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-03T14:39:49Z

PR_Github #20584 [ run ] completed with state ABORTED
LLM/main/L0_MergeRequest_PR #15538 (Blue Ocean) completed with status: ABORTED

ixlmar · 2025-10-03T16:38:46Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-03T16:43:57Z

PR_Github #20605 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-03T16:44:00Z

PR_Github #20590 [ run ] completed with state ABORTED
LLM/main/L0_MergeRequest_PR #15543 (Blue Ocean) completed with status: ABORTED

tensorrt-cicd · 2025-10-03T19:41:10Z

PR_Github #20605 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15554 completed with status: 'FAILURE'

ixlmar · 2025-10-06T06:38:59Z

/bot run

tensorrt-cicd · 2025-10-06T06:44:21Z

PR_Github #20663 [ run ] triggered by Bot

dcampora

LGTM

tensorrt-cicd · 2025-10-06T11:29:15Z

PR_Github #20663 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15606 completed with status: 'FAILURE'

ixlmar · 2025-10-06T11:32:45Z

/bot run

tensorrt-cicd · 2025-10-06T11:38:31Z

PR_Github #20670 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-06T13:09:40Z

PR_Github #20670 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15613 completed with status: 'SUCCESS'

ixlmar marked this pull request as ready for review October 2, 2025 16:41

ixlmar requested review from Funatiq and dcampora October 2, 2025 16:41

ixlmar marked this pull request as draft October 3, 2025 10:53

chore: resolve sampling defaults in OpenAI API backend

ab07b4c

Signed-off-by: ixlmar <206748156+ixlmar@users.noreply.github.com>

ixlmar force-pushed the chore/robust-openai-api-defaults branch from aa97b54 to ab07b4c Compare October 3, 2025 11:00

ixlmar marked this pull request as ready for review October 3, 2025 12:37

DomBrown approved these changes Oct 3, 2025

View reviewed changes

DomBrown enabled auto-merge (squash) October 3, 2025 16:06

dcampora approved these changes Oct 6, 2025

View reviewed changes

Funatiq approved these changes Oct 6, 2025

View reviewed changes

DomBrown merged commit 98b3af4 into NVIDIA:main Oct 6, 2025
5 checks passed

ixlmar deleted the chore/robust-openai-api-defaults branch October 6, 2025 13:10

[TRTLLM-8413][chore] resolve sampling defaults in OpenAI API backend #8121

[TRTLLM-8413][chore] resolve sampling defaults in OpenAI API backend #8121

Uh oh!

Conversation

ixlmar commented Oct 2, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Summary by CodeRabbit

Uh oh!

ixlmar commented Oct 2, 2025

Uh oh!

tensorrt-cicd commented Oct 2, 2025

Uh oh!

coderabbitai bot commented Oct 2, 2025

Walkthrough

Changes

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

tensorrt-cicd commented Oct 2, 2025

Uh oh!

ixlmar commented Oct 3, 2025

Uh oh!

tensorrt-cicd commented Oct 3, 2025

Uh oh!

tensorrt-cicd commented Oct 3, 2025

Uh oh!

ixlmar commented Oct 3, 2025

Uh oh!

tensorrt-cicd commented Oct 3, 2025

Uh oh!

ixlmar commented Oct 3, 2025

Uh oh!

tensorrt-cicd commented Oct 3, 2025

Uh oh!

tensorrt-cicd commented Oct 3, 2025

Uh oh!

ixlmar commented Oct 3, 2025

Uh oh!

tensorrt-cicd commented Oct 3, 2025

Uh oh!

tensorrt-cicd commented Oct 3, 2025

Uh oh!

ixlmar commented Oct 3, 2025

Uh oh!

tensorrt-cicd commented Oct 3, 2025

Uh oh!

tensorrt-cicd commented Oct 3, 2025

Uh oh!

tensorrt-cicd commented Oct 3, 2025

Uh oh!

ixlmar commented Oct 6, 2025

Uh oh!

tensorrt-cicd commented Oct 6, 2025

Uh oh!

dcampora left a comment

Choose a reason for hiding this comment

Uh oh!

tensorrt-cicd commented Oct 6, 2025

Uh oh!

ixlmar commented Oct 6, 2025

Uh oh!

tensorrt-cicd commented Oct 6, 2025

Uh oh!

tensorrt-cicd commented Oct 6, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

ixlmar commented Oct 2, 2025 •

edited by coderabbitai bot

Loading