[https://nvbugs/5628204][fix] Stop token IDs - fast path optimization for single stop token IDs only #9014
Conversation
📝 WalkthroughWalkthroughThe changes enhance stop token criteria matching in the Torch sampler by incorporating the newly generated token into evaluation logic. A fast-path optimization for single-token stop words is added alongside multi-token stop word handling. Test coverage is expanded with new test cases and helper functions to validate stop token behavior. Changes
Sequence DiagramsequenceDiagram
participant Sampler as TorchSampler
participant StopCriteria as _handle_stop_criteria()
participant MeetCriteria as _meet_stop_token_criteria()
participant Check as Stop Word Matching
Sampler->>StopCriteria: call with request, new_token
StopCriteria->>MeetCriteria: pass request, new_token
alt Fast Path: Single-Token Stop Words
MeetCriteria->>Check: Check new_token against stop_words_list
Check-->>MeetCriteria: Match found or not
else Multi-Token Stop Words
MeetCriteria->>Check: Match using sequence logic
Check-->>MeetCriteria: Match found or not
end
MeetCriteria-->>StopCriteria: Return criteria met (bool)
StopCriteria-->>Sampler: Return stop decision
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes
Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 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: 1
🧹 Nitpick comments (1)
tests/unittest/_torch/sampler/test_trtllm_sampler.py (1)
84-116: Consider renaming test for clarity.The test name
test_trtllm_sampler_with_stop_token_idssuggests it tests the TRTLLM sampler, but it actually tests the Torch sampler (viacreate_llm_with_torch_samplerwhich setsenable_trtllm_sampler=False). The test correctly validates the fast-path optimization added toTorchSampler._meet_stop_token_criteria.Consider renaming to
test_torch_sampler_with_stop_token_idsfor consistency with the other test at line 119.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
tensorrt_llm/_torch/pyexecutor/sampler.py(2 hunks)tests/integration/test_lists/test-db/l0_a10.yml(1 hunks)tests/unittest/_torch/sampler/test_trtllm_sampler.py(3 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/_torch/pyexecutor/sampler.pytests/unittest/_torch/sampler/test_trtllm_sampler.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/_torch/pyexecutor/sampler.pytests/unittest/_torch/sampler/test_trtllm_sampler.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/_torch/pyexecutor/sampler.pytests/unittest/_torch/sampler/test_trtllm_sampler.py
🧠 Learnings (13)
📓 Common learnings
Learnt from: djns99
Repo: NVIDIA/TensorRT-LLM PR: 6915
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu:4010-4012
Timestamp: 2025-08-14T23:23:27.449Z
Learning: For MOE (Mixture of Experts) code reviews in TensorRT-LLM, avoid repeatedly suggesting finalize fusion validation checks and safety assertions. The user djns99 has indicated these suggestions are repetitive and unwanted across multiple MOE-related changes.
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: 2025-09-09T09:40:45.658Z
Learnt from: fredricz-20070104
Repo: NVIDIA/TensorRT-LLM PR: 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/test-db/l0_a10.ymltests/unittest/_torch/sampler/test_trtllm_sampler.py
📚 Learning: 2025-09-17T02:48:52.732Z
Learnt from: tongyuantongyu
Repo: NVIDIA/TensorRT-LLM PR: 7781
File: tests/integration/test_lists/waives.txt:313-313
Timestamp: 2025-09-17T02:48:52.732Z
Learning: In TensorRT-LLM, `tests/integration/test_lists/waives.txt` is specifically for waiving/skipping tests, while other test list files like those in `test-db/` and `qa/` directories are for different test execution contexts (pre-merge, post-merge, QA tests). The same test appearing in both waives.txt and execution list files is intentional - the test is part of test suites but will be skipped due to the waiver.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.yml
📚 Learning: 2025-08-06T13:58:07.506Z
Learnt from: galagam
Repo: NVIDIA/TensorRT-LLM PR: 6487
File: tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py:1-12
Timestamp: 2025-08-06T13:58:07.506Z
Learning: In TensorRT-LLM, test files (files under tests/ directories) do not require NVIDIA copyright headers, unlike production source code files. Test files typically start directly with imports, docstrings, or code.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.ymltests/unittest/_torch/sampler/test_trtllm_sampler.py
📚 Learning: 2025-08-26T09:49:04.956Z
Learnt from: pengbowang-nv
Repo: NVIDIA/TensorRT-LLM PR: 7192
File: tests/integration/test_lists/test-db/l0_dgx_b200.yml:56-72
Timestamp: 2025-08-26T09:49:04.956Z
Learning: In TensorRT-LLM test configuration files, the test scheduling system handles wildcard matching with special rules that prevent duplicate test execution even when the same tests appear in multiple yaml files with overlapping GPU wildcards (e.g., "*b200*" and "*gb200*").
Applied to files:
tests/integration/test_lists/test-db/l0_a10.ymltests/unittest/_torch/sampler/test_trtllm_sampler.py
📚 Learning: 2025-10-22T06:53:47.017Z
Learnt from: xinhe-nv
Repo: NVIDIA/TensorRT-LLM PR: 8534
File: scripts/format_test_list.py:1-6
Timestamp: 2025-10-22T06:53:47.017Z
Learning: The file `scripts/format_test_list.py` in the TensorRT-LLM repository does not require the NVIDIA Apache-2.0 copyright header.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.yml
📚 Learning: 2025-08-29T14:07:45.863Z
Learnt from: EmmaQiaoCh
Repo: NVIDIA/TensorRT-LLM PR: 7370
File: tests/unittest/trt/model_api/test_model_quantization.py:24-27
Timestamp: 2025-08-29T14:07:45.863Z
Learning: In TensorRT-LLM's CI infrastructure, pytest skip markers (pytest.mark.skip) are properly honored even when test files have __main__ blocks that call test functions directly. The testing system correctly skips tests without requiring modifications to the __main__ block execution pattern.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.ymltests/unittest/_torch/sampler/test_trtllm_sampler.py
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
Repo: NVIDIA/TensorRT-LLM PR: 6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.ymltests/unittest/_torch/sampler/test_trtllm_sampler.py
📚 Learning: 2025-08-11T20:09:24.389Z
Learnt from: achartier
Repo: NVIDIA/TensorRT-LLM PR: 6763
File: tests/integration/defs/triton_server/conftest.py:16-22
Timestamp: 2025-08-11T20:09:24.389Z
Learning: In the TensorRT-LLM test infrastructure, the team prefers simple, direct solutions (like hard-coding directory traversal counts) over more complex but robust approaches when dealing with stable directory structures. They accept the maintenance cost of updating tests if the layout changes.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.ymltests/unittest/_torch/sampler/test_trtllm_sampler.py
📚 Learning: 2025-08-01T15:14:45.673Z
Learnt from: yibinl-nvidia
Repo: NVIDIA/TensorRT-LLM PR: 6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.
Applied to files:
tests/integration/test_lists/test-db/l0_a10.yml
📚 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/_torch/pyexecutor/sampler.py
📚 Learning: 2025-08-26T09:37:10.463Z
Learnt from: jiaganc
Repo: NVIDIA/TensorRT-LLM PR: 7031
File: tensorrt_llm/bench/dataclasses/configuration.py:90-104
Timestamp: 2025-08-26T09:37:10.463Z
Learning: In TensorRT-LLM's bench configuration, the `get_pytorch_perf_config()` method returns `self.pytorch_config` which is a Dict[str, Any] that can contain default values including `cuda_graph_config`, making the fallback `llm_args["cuda_graph_config"]` safe to use.
Applied to files:
tests/unittest/_torch/sampler/test_trtllm_sampler.py
📚 Learning: 2025-08-26T09:37:10.463Z
Learnt from: jiaganc
Repo: NVIDIA/TensorRT-LLM PR: 7031
File: tensorrt_llm/bench/dataclasses/configuration.py:90-104
Timestamp: 2025-08-26T09:37:10.463Z
Learning: In TensorRT-LLM, the `get_pytorch_perf_config()` method returns `self.pytorch_config` which can contain default `cuda_graph_config` values, so `llm_args` may already have this config before the extra options processing.
Applied to files:
tests/unittest/_torch/sampler/test_trtllm_sampler.py
🧬 Code graph analysis (2)
tensorrt_llm/_torch/pyexecutor/sampler.py (1)
tensorrt_llm/_torch/pyexecutor/llm_request.py (1)
LlmRequest(293-465)
tests/unittest/_torch/sampler/test_trtllm_sampler.py (1)
tests/unittest/_torch/executor/test_overlap_scheduler.py (2)
create_llm(24-41)model_path(20-21)
🪛 Ruff (0.14.3)
tests/unittest/_torch/sampler/test_trtllm_sampler.py
147-147: Use explicit conversion flag
Replace with conversion flag
(RUF010)
⏰ 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 (4)
tensorrt_llm/_torch/pyexecutor/sampler.py (2)
817-836: Fast-path optimization looks good.The optimization correctly identifies when all stop words are single tokens and avoids loading all tokens via
request.get_tokens(0). Themax_stop_word_lengthcomputation is accurate, and the fast-path logic (lines 831-834) correctly checks only the new token against the stop words list.Minor performance note: The
inoperator on a list is O(n). If performance profiling shows this is a bottleneck with many stop words, consider convertingstop_words_listto a set for O(1) lookup. However, this is still significantly faster than loading all tokens, so the optimization is effective as-is.
849-861: LGTM: Correctly passes new token to stop criteria check.The call site correctly passes the
new_tokenparameter to_meet_stop_token_criteria, enabling the fast-path optimization for single-token stop words.tests/integration/test_lists/test-db/l0_a10.yml (1)
19-19: LGTM: Test list correctly updated.The new test file is appropriately added to the PyTorch tests section to ensure coverage of the sampler optimization in CI.
tests/unittest/_torch/sampler/test_trtllm_sampler.py (1)
118-147: LGTM: Multi-token stop word test is well-designed.The test correctly validates the slow-path handling of multi-token stop words, ensuring the stop string doesn't appear in the output. The test logic is sound and properly exercises the updated
_meet_stop_token_criteriamethod.
|
/bot run |
|
PR_Github #23871 [ run ] triggered by Bot. Commit: |
|
PR_Github #23871 [ run ] completed with state |
|
/bot run |
|
PR_Github #23877 [ run ] triggered by Bot. Commit: |
|
PR_Github #23877 [ run ] completed with state |
Signed-off-by: Michal Guzek <[email protected]>
moraxu
force-pushed
the
dev-mguzek-fix-stop-tokens-bottleneck
branch
from
588cc09 to
af7cf97
Compare
|
/bot run |
|
PR_Github #24049 [ run ] triggered by Bot. Commit: |
|
PR_Github #24049 [ run ] completed with state |
Signed-off-by: Michal Guzek <[email protected]>
|
/bot run |
|
PR_Github #24056 [ run ] triggered by Bot. Commit: |
|
PR_Github #24056 [ run ] completed with state |
2 participants
Summary by CodeRabbit
New Features
Tests
Description
Stop token IDs - fast path optimization (for single stop token IDs only) to prevent unnecessarily loading of all the tokens at each step.
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
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.