[TRTLLM-5235][feat] Enable regex and EBNF grammar in trtllm-serve #7925
Conversation
|
/bot run |
|
PR_Github #19683 [ run ] triggered by Bot |
📝 WalkthroughWalkthroughAdds support for "regex" and "ebnf" response formats in the OpenAI-compatible server, mapping them to guided decoding parameters. Updates request descriptions. Reworks and expands unit and integration tests to validate regex, EBNF, JSON schema, and structural tag behaviors; removes legacy JSON test and updates test lists and e2e launcher. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant C as Client
participant S as OpenAI-Compatible Server
participant P as ResponseFormat→Guided Params
participant D as Decoder/LLM Backend
C->>S: chat.completions.create(messages, response_format)
S->>P: map response_format
alt regex
P-->>S: GuidedDecodingParams(regex=...)
else ebnf
P-->>S: GuidedDecodingParams(grammar=...)
else json/json_object/structural_tag/text
P-->>S: GuidedDecodingParams(...existing...)
end
S->>D: generate(messages, guided_params)
D-->>S: tokens/content
S-->>C: completion(response, usage)
note over S,D: Mapping updated to support "regex" and "ebnf"
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests
Tip 👮 Agentic pre-merge checks are now available in preview!Pro plan users can now enable pre-merge checks in their settings to enforce checklists before merging PRs.
Please see the documentation for more information. Example: reviews:
pre_merge_checks:
custom_checks:
- name: "Undocumented Breaking Changes"
mode: "warning"
instructions: |
Pass/fail criteria: All breaking changes to public APIs, CLI flags, environment variables, configuration keys, database schemas, or HTTP/GraphQL endpoints must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md. Exclude purely internal or private changes (e.g., code not exported from package entry points or explicitly marked as internal).Please share your feedback with us on this Discord post. 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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (3)
tensorrt_llm/serve/openai_protocol.py (1)
89-96: Keep the type comment in sync with supported values.The inline comment still lists only text/json/json_object/structural_tag. Update to include regex and ebnf for clarity.
-class ResponseFormat(OpenAIBaseModel): - # type must be one of "text", "json", "json_object", or "structural_tag" +class ResponseFormat(OpenAIBaseModel): + # type must be one of: "text", "json", "json_object", "regex", "ebnf", or "structural_tag"tests/unittest/llmapi/apps/_test_openai_chat_guided_decoding.py (2)
1-2: Add NVIDIA Apache-2.0 SPDX header.New Python files must include the project header.
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. +# SPDX-License-Identifier: Apache-2.0
182-207: Tighten the regex to avoid partial matches.Anchor the pattern and use fullmatch to ensure the whole output is guided (no extra text).
- chat_completion = client.chat.completions.create( + chat_completion = client.chat.completions.create( model=model_name, messages=messages, max_completion_tokens=256, response_format={ "type": "regex", - "regex": "(Paris|London)" + "regex": "^(Paris|London)$" }, ) @@ - assert re.match(r"(Paris|London)", message.content) + assert re.fullmatch(r"(Paris|London)", message.content)
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (6)
tensorrt_llm/serve/openai_protocol.py(3 hunks)tests/integration/defs/test_e2e.py(1 hunks)tests/integration/test_lists/qa/llm_function_core.txt(1 hunks)tests/integration/test_lists/test-db/l0_a10.yml(1 hunks)tests/unittest/llmapi/apps/_test_openai_chat_guided_decoding.py(3 hunks)tests/unittest/llmapi/apps/_test_openai_chat_json.py(0 hunks)
💤 Files with no reviewable changes (1)
- tests/unittest/llmapi/apps/_test_openai_chat_json.py
🧰 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.pytests/integration/defs/test_e2e.pytests/unittest/llmapi/apps/_test_openai_chat_guided_decoding.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.pytests/integration/defs/test_e2e.pytests/unittest/llmapi/apps/_test_openai_chat_guided_decoding.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.pytests/integration/defs/test_e2e.pytests/unittest/llmapi/apps/_test_openai_chat_guided_decoding.py
🧠 Learnings (1)
📚 Learning: 2025-09-09T09:40:45.658Z
Learnt from: fredricz-20070104
PR: NVIDIA/TensorRT-LLM#7645
File: tests/integration/test_lists/qa/llm_function_core.txt:648-648
Timestamp: 2025-09-09T09:40:45.658Z
Learning: In TensorRT-LLM test lists, it's common and intentional for the same test to appear in multiple test list files when they serve different purposes (e.g., llm_function_core.txt for comprehensive core functionality testing and llm_function_core_sanity.txt for quick sanity checks). This duplication allows tests to be run in different testing contexts.
Applied to files:
tests/integration/test_lists/qa/llm_function_core.txt
🧬 Code graph analysis (2)
tensorrt_llm/serve/openai_protocol.py (1)
tensorrt_llm/sampling_params.py (1)
GuidedDecodingParams(14-36)
tests/integration/defs/test_e2e.py (1)
tests/integration/defs/conftest.py (4)
llm_root(181-182)llm_venv(691-708)test_root(2203-2204)unittest_path(89-90)
🪛 Ruff (0.13.1)
tests/integration/defs/test_e2e.py
1680-1680: Unused function argument: llm_root
(ARG001)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
🔇 Additional comments (3)
tests/integration/test_lists/qa/llm_function_core.txt (1)
620-620: Good addition: guided decoding e2e test included in core list.This aligns the QA suite with the new regex/EBNF support.
tests/integration/test_lists/test-db/l0_a10.yml (1)
28-28: Pre-merge coverage updated to guided decoding.Replacing older JSON/structural-tag examples with
test_openai_chat_guided_decodingin pre_merge looks correct.tensorrt_llm/serve/openai_protocol.py (1)
257-260: Docs string updated correctly.The
CompletionRequest.response_formatdescription now reflects regex and ebnf support.
|
/bot run |
|
PR_Github #19684 [ run ] triggered by Bot |
|
PR_Github #19683 [ run ] completed with state |
|
PR_Github #19684 [ run ] completed with state |
4 participants
Summary by CodeRabbit
Description
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 thestage-listparameter 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.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip 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-pipelineReuse 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.