[https://nvbugs/5772521][fix] Fix draft token tree chain crash #10386

mikeiovine · 2026-01-02T19:23:37Z

Description

Corner case where the user specifies a chain topology like [[0], [0, 0]] was crashing due to the wrong step being used in the sampler.

Test Coverage

Skipped to save on CI time. This is not a case that is really used in practice (should use max_draft_len=... + eagle_choices=None instead).

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.

Details

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

Bug Fixes
- Improved accuracy of step value tracking in token sampling logic to ensure precise path indexing.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>

mikeiovine · 2026-01-02T19:23:49Z

/bot run --disable-fail-fast

coderabbitai · 2026-01-02T19:26:25Z

📝 Walkthrough

Walkthrough

The change modifies tree-based draft token processing in the sampler to use the actual path index value (from idx.item()) as the step parameter passed to add_token and finish_if_reason, replacing the previously used incremented draft-token counter. Control flow remains unchanged; only the step value calculation is refined to align with the specific path index rather than a separate accumulation counter.

Changes

Cohort / File(s)	Summary
Draft token step tracking `tensorrt_llm/_torch/pyexecutor/sampler.py`	Modified tree-based draft token processing to forward actual path index step value (derived from `idx.item()`) to `add_token` and `finish_if_reason`, replacing incremented draft-token counter logic

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the specific fix being applied—resolving a crash in draft token tree chain processing—directly aligned with the code changes to the sampler.
Description check	✅ Passed	The description explains the issue (chain topology crash caused by wrong step in sampler) and the solution approach, though it lacks detail about the underlying root cause and reasoning for skipping tests.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

✨ Finishing touches

📝 Generate docstrings

📜 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 bdf6953 and 927e975.

📒 Files selected for processing (1)

tensorrt_llm/_torch/pyexecutor/sampler.py

🧰 Additional context used

📓 Path-based instructions (2)

**/*.py

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.py: 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
Python files should use snake_case naming: some_file.py
Python classes should use PascalCase naming: class SomeClass
Python functions and methods should use snake_case naming: def my_awesome_function():
Python local variables should use snake_case naming: my_variable = ...
Python variable names that start with a number should be prefixed with 'k': k_99th_percentile = ...
Python global variables should use upper snake_case with prefix 'G': G_MY_GLOBAL = ...
Python constants should use upper snake_case naming: 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 in Python for classes and functions, which can be parsed by Sphinx
Python attributes and variables can be documented inline with type and description
Avoid using reflection in Python when functionality can be easily achieved without reflection
When using try-except blocks in Python, limit the except to the smallest set of errors possible
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, using the else block for logic

Files:

tensorrt_llm/_torch/pyexecutor/sampler.py

**/*.{cpp,h,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the year of its latest meaningful modification

Files:

tensorrt_llm/_torch/pyexecutor/sampler.py

🧠 Learnings (4)

📚 Learning: 2025-08-28T10:25:22.370Z

Learnt from: ixlmar
Repo: NVIDIA/TensorRT-LLM PR: 7294
File: tensorrt_llm/_torch/pyexecutor/sampler.py:887-891
Timestamp: 2025-08-28T10:25:22.370Z
Learning: In tensorrt_llm/_torch/pyexecutor/sampler.py, the draft_probs and target_probs tensors have shapes [1, steps] not [steps, vocab_size] as might be expected, making the .squeeze(0) operations appropriate for removing the batch dimension of size 1.

Applied to files:

tensorrt_llm/_torch/pyexecutor/sampler.py

📚 Learning: 2025-12-12T03:27:18.859Z

Learnt from: tongyuantongyu
Repo: NVIDIA/TensorRT-LLM PR: 9655
File: tensorrt_llm/_torch/pyexecutor/sampler.py:3031-3031
Timestamp: 2025-12-12T03:27:18.859Z
Learning: In tensorrt_llm/_torch/pyexecutor/sampler.py, when reviewing code that iterates through requests, ensure it does not convert excessive data into Python lists. Instead, the code should use torch.gather or indexing to gather only the data that will be used in the for loop before converting to Python lists. This minimizes data movement and improves performance.

Applied to files:

tensorrt_llm/_torch/pyexecutor/sampler.py

📚 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: 2025-12-12T03:27:08.565Z

Learnt from: tongyuantongyu
Repo: NVIDIA/TensorRT-LLM PR: 9655
File: tensorrt_llm/_torch/pyexecutor/sampler.py:3031-3031
Timestamp: 2025-12-12T03:27:08.565Z
Learning: In files under tensorrt_llm/_torch/pyexecutor, avoid accessing torch.Tensor objects inside for-loops when iterating over requests. Convert batched tensors to Python lists beforehand using tensor.tolist(), and then iterate over those lists. This improves performance by reducing tensor-bound operations inside hot loops. Apply this pattern to similar code paths that process batches to access simple Python data structures (lists) inside loops.

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 (1)

tensorrt_llm/_torch/pyexecutor/sampler.py (1)

1300-1310: LGTM! Fix correctly uses path index instead of counter.

The change properly addresses the corner case crash by using the actual tree node index (idx.item()) as the step parameter, rather than a sequential counter. This ensures correct indexing into both new_tokens[step] and finish_reasons[...][step] arrays, which is essential for non-sequential tree topologies like [[0], [0, 0]].

The separation of concerns is well-maintained:

step - actual tree position for array indexing

num_accepted_draft_tokens - acceptance count tracker

Minor note: The .item() call inside the loop performs a device-to-host sync per iteration. Based on learnings, this could be optimized by extracting all indices at once before the loop. However, for the typical number of accepted tokens in speculative decoding (usually < 10), the performance impact is negligible.

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 · 2026-01-02T19:29:31Z

PR_Github #30408 [ run ] triggered by Bot. Commit: 927e975

tensorrt-cicd · 2026-01-02T22:50:54Z

PR_Github #30408 [ run ] completed with state SUCCESS. Commit: 927e975
/LLM/main/L0_MergeRequest_PR pipeline #23436 completed with status: 'SUCCESS'

…A#10386) Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Daniil Kulko <kulkodaniil@gmail.com>

[https://nvbugs/5772521][fix] Fix draft token tree chain crash

927e975

Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>

mikeiovine requested review from a team and kris1025 and removed request for a team January 2, 2026 19:23

mikeiovine requested a review from a team as a code owner January 2, 2026 19:23

mikeiovine requested a review from joyang-nv January 2, 2026 19:23

mikeiovine mentioned this pull request Jan 2, 2026

[Bug]: Eagle static chain-like draft token tree raise Exception #10325

Closed

5 tasks

MartinMarciniszyn approved these changes Jan 5, 2026

View reviewed changes

MartinMarciniszyn merged commit bedfff4 into NVIDIA:main Jan 5, 2026
7 checks passed

mikeiovine deleted the fix-chain-drafts branch January 5, 2026 16:23

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[https://nvbugs/5772521][fix] Fix draft token tree chain crash #10386

[https://nvbugs/5772521][fix] Fix draft token tree chain crash #10386

Uh oh!

mikeiovine commented Jan 2, 2026 •

edited by coderabbitai bot

Loading

Uh oh!

mikeiovine commented Jan 2, 2026

Uh oh!

coderabbitai bot commented Jan 2, 2026

Walkthrough

Changes

Estimated code review effort

Uh oh!

tensorrt-cicd commented Jan 2, 2026

Uh oh!

tensorrt-cicd commented Jan 2, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

[https://nvbugs/5772521][fix] Fix draft token tree chain crash #10386

[https://nvbugs/5772521][fix] Fix draft token tree chain crash #10386

Uh oh!

Conversation

mikeiovine commented Jan 2, 2026 • 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!

mikeiovine commented Jan 2, 2026

Uh oh!

coderabbitai bot commented Jan 2, 2026

Walkthrough

Changes

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

tensorrt-cicd commented Jan 2, 2026

Uh oh!

tensorrt-cicd commented Jan 2, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

mikeiovine commented Jan 2, 2026 •

edited by coderabbitai bot

Loading