[None] [feat] add eos_token_id in generation_config to sampling params #9514
Conversation
…ord_ids Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
📝 WalkthroughWalkthroughGeneralizes and unifies EOS token ID handling in sampling parameters by removing model-specific logic for kimi_k2 and qwen3_next. The change introduces a consistent approach to integrate EOS token IDs from generation_config into the internal stop-word list across all models, while renaming variables for semantic clarity. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
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: 2
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tensorrt_llm/sampling_params.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: The code developed for TensorRT-LLM should conform to Python 3.8+
Indent Python code with 4 spaces; do not use tabs
Always maintain the namespace when importing in Python, even if only one class or function from a module is used (e.g., usefrom package.subpackage import fooand thenfoo.SomeClass()instead offrom package.subpackage.foo import SomeClass)
Python filenames should use snake_case (e.g.,some_file.py)
Python class names should use PascalCase (e.g.,class SomeClass)
Python function and method names should use snake_case (e.g.,def my_awesome_function():)
Python local variable names should use snake_case, with prefixkfor variable names that start with a number (e.g.,k_99th_percentile = ...)
Python global variables should use upper snake_case with prefixG(e.g.,G_MY_GLOBAL = ...)
Python constants should use upper snake_case (e.g.,MY_CONSTANT = ...)
Avoid shadowing variables declared in an outer scope in Python
Initialize all externally visible members of a Python class in the constructor
For Python interfaces that may be used outside a file, prefer docstrings over comments
Python comments should be reserved for code within a function, or interfaces that are local to a file
Use Google style docstrings for Python classes and functions, which can be parsed by Sphinx
Python attributes and variables can be documented inline with type and description (e.g.,self.x = 5followed by"""<type>: Description of 'x'""")
Avoid using reflection in Python when functionality can be easily achieved without reflection
When using try-except blocks in Python, limit the except clause to the smallest set of specific errors possible instead of catching all exceptions
When using try-except blocks in Python to handle multiple possible variable types (duck-typing), keep the body of the try as small as possible and use the else block to implement the logic
Files:
tensorrt_llm/sampling_params.py
**/*.{cpp,h,cu,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code files should contain an NVIDIA copyright header that includes the current year at the top
Files:
tensorrt_llm/sampling_params.py
🧠 Learnings (2)
📓 Common learnings
Learnt from: samuellees
Repo: NVIDIA/TensorRT-LLM PR: 6974
File: tensorrt_llm/serve/scripts/benchmark_dataset.py:558-566
Timestamp: 2025-08-18T08:42:02.640Z
Learning: In TensorRT-LLM's RandomDataset (tensorrt_llm/serve/scripts/benchmark_dataset.py), when using --random-token-ids option, sequence length accuracy is prioritized over semantic correctness for benchmarking purposes. The encode/decode operations should use skip_special_tokens=True and add_special_tokens=False to ensure exact target token lengths.
📚 Learning: 2025-08-18T08:42:02.640Z
Learnt from: samuellees
Repo: NVIDIA/TensorRT-LLM PR: 6974
File: tensorrt_llm/serve/scripts/benchmark_dataset.py:558-566
Timestamp: 2025-08-18T08:42:02.640Z
Learning: In TensorRT-LLM's RandomDataset (tensorrt_llm/serve/scripts/benchmark_dataset.py), when using --random-token-ids option, sequence length accuracy is prioritized over semantic correctness for benchmarking purposes. The encode/decode operations should use skip_special_tokens=True and add_special_tokens=False to ensure exact target token lengths.
Applied to files:
tensorrt_llm/sampling_params.py
⏰ 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 (2)
tensorrt_llm/sampling_params.py (2)
394-398: LGTM: Proper normalization of eos_token_id.The logic correctly normalizes
eos_token_idto a list format, handling both integer and list inputs as documented in the Hugging Face API.
400-409: Repository access unavailable—manual verification required.The verification script cannot execute due to repository cloning failures. Therefore, I cannot definitively verify the key claims in the review comment:
- Whether model-specific logic for kimi_k2 and qwen3_next was actually removed
- Whether the generalized EOS token handling doesn't regress behavior for those models
- Whether any remaining model-specific EOS handling conflicts exist elsewhere in the codebase
The original review comment requests verification of generalized EOS token handling across models, but this verification cannot be completed without access to the codebase to search for references to
kimi_k2,qwen3_next, and related EOS token handling logic.
| # Add eos_token_id in generation_config to _stop_word_ids | ||
| # Refer to https://huggingface.co/docs/hub/en/transformers#transformers-repository-files and | ||
| # https://github.com/huggingface/transformers/blob/1ae4d917ed3badbdb1ffc167e0529f5a6d3c080d/src/transformers/generation/stopping_criteria.py#L451C1-L451C42 | ||
| # The eos_token_id in generation_config are really mean to stop the text generation. |
There was a problem hiding this comment.
Fix grammatical error in comment.
Line 393 contains a grammatical error: "are really mean to stop" should be "really means to stop" or "are really meant to stop".
Apply this diff:
- # The eos_token_id in generation_config are really mean to stop the text generation.
+ # The eos_token_id in generation_config are really meant to stop the text generation.🤖 Prompt for AI Agents
In tensorrt_llm/sampling_params.py around lines 390 to 393, the comment has a
grammatical error: change the phrase "are really mean to stop the text
generation." to a correct form such as "are really meant to stop the text
generation." Update the comment line to use "meant" (or alternatively "mean") so
the sentence reads grammatically correct while preserving the original meaning.
| if self._stop_word_ids is None: | ||
| self._stop_word_ids = [generation_eos_token_ids] | ||
| else: | ||
| all_stop_tokens_id = set(i for sublist in self._stop_word_ids for i in sublist) |
There was a problem hiding this comment.
Use plural variable name for consistency.
The variable all_stop_tokens_id contains multiple token IDs (it's a set of IDs), so it should be named all_stop_token_ids for consistency with Python naming conventions.
Apply this diff:
- all_stop_tokens_id = set(i for sublist in self._stop_word_ids for i in sublist)
+ all_stop_token_ids = set(i for sublist in self._stop_word_ids for i in sublist)
from_generation_stop_token_ids = [
- i for i in generation_eos_token_ids if i not in all_stop_tokens_id
+ i for i in generation_eos_token_ids if i not in all_stop_token_ids
]📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| all_stop_tokens_id = set(i for sublist in self._stop_word_ids for i in sublist) | |
| all_stop_token_ids = set(i for sublist in self._stop_word_ids for i in sublist) | |
| from_generation_stop_token_ids = [ | |
| i for i in generation_eos_token_ids if i not in all_stop_token_ids | |
| ] |
🤖 Prompt for AI Agents
In tensorrt_llm/sampling_params.py around line 403, rename the variable
all_stop_tokens_id to the plural form all_stop_token_ids to reflect that it
holds multiple token IDs; update its declaration and every subsequent reference
in the file to use all_stop_token_ids to maintain consistency with naming
conventions and avoid NameError.
|
/bot run |
|
PR_Github #26611 [ run ] triggered by Bot. Commit: |
|
PR_Github #26611 [ run ] completed with state |
|
/bot run |
|
PR_Github #26682 [ run ] triggered by Bot. Commit: |
|
PR_Github #26682 [ run ] completed with state |
|
/bot run |
|
PR_Github #26708 [ run ] triggered by Bot. Commit: |
|
PR_Github #26708 [ run ] completed with state |
|
/bot run |
|
PR_Github #27046 [ run ] triggered by Bot. Commit: |
2 participants
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.
Description
LLMs' generation criteria of stop token is only set by tokenizer.eos_token_id and users' definition. It should also use the eos_token_id in generation_config.json. This PR adds related functional support. Model's eos_token_id in generation_config.json will be added to SamplingParams._stop_word_ids during setup.
Supporting materials: link.
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
Update tava architecture diagram if there is a significant design change in PR.
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.