[None][fix] Fix access to new tokens in sampler. #7958
Conversation
📝 WalkthroughWalkthroughReplaces direct writes to the new_tokens buffer during rejection-sampling handling with request.add_new_token calls. Adjusts the sample_last branch to use add_new_token when applicable, otherwise falls back to add_token with step indexing. Stop criteria checks and beam logic remain unchanged. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant Sampler
participant Request
participant StopCriteria as Stop Criteria
rect rgb(245,248,255)
Sampler->>Request: add_new_token(new_token, beam)
Request-->>Sampler: ack
Sampler->>StopCriteria: check after each token
StopCriteria-->>Sampler: continue / stop
end
alt sample_last == true
Sampler->>Request: add_new_token(new_token, beam)
Request-->>Sampler: ack
else sample_last == false
Note over Sampler: Use legacy buffer path
Sampler->>Sampler: add_token(request, new_tokens, beam, step=num_accepted)
end
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests
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)
tensorrt_llm/_torch/pyexecutor/sampler.py (1)
895-901: Type hint drift: new_tokens is a nested list here, not a torch.Tensorprocess_draft_tokens_rejection_sampling (and the greedy variant) consume new_tokens coming from state.host.new_tokens.tolist(), i.e., list[list[list[int]]], but the signature says torch.Tensor. Adjust the annotation to avoid confusion and catch misuse.
Example:
-def _process_draft_tokens_rejection_sampling( - self, request: LlmRequest, new_tokens: torch.Tensor) -> int: +def _process_draft_tokens_rejection_sampling( + self, request: LlmRequest, new_tokens: list[list[list[int]]]) -> int:And similarly for _process_draft_tokens_greedy.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tensorrt_llm/_torch/pyexecutor/sampler.py(1 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.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.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.py
🧠 Learnings (2)
📓 Common learnings
Learnt from: eopXD
PR: NVIDIA/TensorRT-LLM#6767
File: cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp:0-0
Timestamp: 2025-08-15T06:46:54.897Z
Learning: In cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp addToken function, newly allocated blocks are unshared by design. The beam search path in addToken (when sequence.getNumTokens() > windowSize) is currently broken/non-functional with SWA, so the block allocation doesn't follow a shared-then-unshared pattern.
📚 Learning: 2025-08-15T06:46:54.897Z
Learnt from: eopXD
PR: NVIDIA/TensorRT-LLM#6767
File: cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp:0-0
Timestamp: 2025-08-15T06:46:54.897Z
Learning: In cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp addToken function, newly allocated blocks are unshared by design. The beam search path in addToken (when sequence.getNumTokens() > windowSize) is currently broken/non-functional with SWA, so the block allocation doesn't follow a shared-then-unshared pattern.
Applied to files:
tensorrt_llm/_torch/pyexecutor/sampler.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/_torch/pyexecutor/sampler.py (2)
914-919: Good fix: use request.add_new_token for accepted draftsSwitching from in-place writes into new_tokens to request.add_new_token(new_token, beam) is the right abstraction and avoids issues with inference-mode tensors and state desync on the request object.
922-930: LGTM on sample_last vs. fallback pathUsing request.add_new_token for the sampled-last token and falling back to add_token(..., step=num_accepted) when all drafts are accepted is correct and keeps request state consistent.
|
/bot run |
|
PR_Github #19802 [ run ] triggered by Bot |
|
PR_Github #19802 [ run ] completed with state |
|
/bot run |
|
PR_Github #19812 [ run ] triggered by Bot |
|
PR_Github #19812 [ run ] completed with state |
Signed-off-by: Daniel Campora <[email protected]>
Signed-off-by: Daniel Campora <[email protected]>
Signed-off-by: Daniel Campora <[email protected]>
Signed-off-by: Daniel Campora <[email protected]>
Signed-off-by: Daniel Campora <[email protected]>
dcampora
force-pushed
the
user/dcampora/fix_sampler_draft_bug
branch
from
7ff6dc8 to
7cafec5
Compare
|
/bot run |
|
PR_Github #20343 [ run ] triggered by Bot |
|
PR_Github #20343 [ run ] completed with state |
|
/bot run |
|
PR_Github #20361 [ run ] triggered by Bot |
|
PR_Github #20361 [ run ] completed with state |
|
/bot run |
|
PR_Github #20525 [ run ] triggered by Bot |
|
PR_Github #20525 [ run ] completed with state |
|
/bot run |
|
PR_Github #20545 [ run ] triggered by Bot |
|
PR_Github #20545 [ run ] completed with state |
Signed-off-by: Daniel Campora <[email protected]>
Signed-off-by: Daniel Campora <[email protected]> Signed-off-by: Faradawn Yang <[email protected]>
Signed-off-by: Daniel Campora <[email protected]>
Signed-off-by: Daniel Campora <[email protected]>
Signed-off-by: Daniel Campora <[email protected]>
Signed-off-by: Daniel Campora <[email protected]>
5 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.