[https://nvbugs/5472947][fix] wait on isend handles before reusing buffers #7462
Conversation
Signed-off-by: Anurag Mukkara <134339030+amukkara@users.noreply.github.com>
amukkara
changed the title
📝 WalkthroughWalkthroughA helper method wait_on_pp_send_handles(microbatch_id) was added to PyExecutor and used to replace direct waits on pipeline-parallel send handles at three call sites: two in _executor_loop_pp (Stages 2 and 3) and one in _handle_logits_communication for the last PP rank. The helper waits and then clears the handle. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant Exec as PyExecutor
participant Next as Next PP Rank
participant Last as (If last rank) Downstream Consumer
rect rgb(245,245,255)
note over Exec: Stage 2 / Stage 3 / Logits handling
Exec->>Exec: wait_on_pp_send_handles(microbatch_id)
alt Handle exists
Exec->>Exec: Wait on handle<br/>(blocks until send completes)
Exec->>Exec: Clear handle (set None)
else No handle
Exec->>Exec: No-op
end
end
rect rgb(240,255,240)
note over Exec,Next: After wait, initiate next nonblocking send
Exec-->>Next: isend_object(payload)
end
opt Last PP rank (logits)
Exec-->>Last: isend_object(logits)
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
✨ 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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tensorrt_llm/_torch/pyexecutor/py_executor.py (1)
909-913: Make the helper private and add minimal docstring/types.For consistency with other internals and clarity, suggest a private name, type hints, and a short docstring.
- def wait_on_pp_send_handles(self, microbatch_id): - if self.send_handles[microbatch_id] is not None: - self.send_handles[microbatch_id].wait() - self.send_handles[microbatch_id] = None + def _wait_on_pp_send_handle(self, microbatch_id: int) -> None: + """Wait for and clear the isend handle for the given microbatch slot.""" + handle = self.send_handles[microbatch_id] + if handle is not None: + handle.wait() + self.send_handles[microbatch_id] = NoneUpdate call sites:
- self.wait_on_pp_send_handles(prev_microbatch_id) + self._wait_on_pp_send_handle(prev_microbatch_id)- self.wait_on_pp_send_handles(prev_microbatch_id) + self._wait_on_pp_send_handle(prev_microbatch_id)- self.wait_on_pp_send_handles(prev_microbatch_id) + self._wait_on_pp_send_handle(prev_microbatch_id)
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
tensorrt_llm/_torch/pyexecutor/py_executor.py(4 hunks)
🧰 Additional context used
📓 Path-based instructions (4)
**/*
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Filenames compiled into a target must be case-insensitively unique
Files:
tensorrt_llm/_torch/pyexecutor/py_executor.py
**/*.{h,hpp,hh,hxx,cc,cpp,cxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Use spaces, not tabs; indent 4 spaces
Files:
tensorrt_llm/_torch/pyexecutor/py_executor.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Code must target Python 3.8+
Indent with 4 spaces; do not use tabs (Python)
Maintain module namespace on import: prefer from package.subpackage import foo; use foo.Symbol()
Python filenames use snake_case
Python class names use PascalCase
Python functions and methods use snake_case
Python local variables use snake_case; if starting with a number concept, prefix with k (e.g., k_99th_percentile)
Python global variables use G_ prefix with UPPER_SNAKE_CASE
Python constants use UPPER_SNAKE_CASE
Avoid shadowing variables from outer scopes
Initialize all externally visible class members in init
For public interfaces, prefer docstrings over comments; comments should be for in-function or file-local interfaces
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes and variables inline with docstrings immediately after assignment
Avoid reflection when a non-reflective approach suffices
Limit except clauses to specific exceptions where possible
When using try/except for duck-typing, keep try body minimal and move logic to else
Files:
tensorrt_llm/_torch/pyexecutor/py_executor.py
**/*.{cpp,cc,cxx,h,hpp,hh,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tensorrt_llm/_torch/pyexecutor/py_executor.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 (4)
tensorrt_llm/_torch/pyexecutor/py_executor.py (4)
861-868: Correctness: wait-before-reuse is right.Calling wait_on_pp_send_handles before reassigning the handle guarantees the prior isend has completed and its buffers aren’t reused prematurely. LGTM.
889-897: Finalize-after-wait prevents premature buffer release.Waiting on the microbatch’s send handle before clearing the slot avoids freeing memory still in use by an in-flight send. Looks good.
1829-1834: Safe reuse guard for logits send—good call.Waiting before posting the logits isend avoids clobbering a prior in-flight handle for the same microbatch ID.
909-913: Centralized send_handles waits: No directsend_handles[].wait()calls were found outsidewait_on_pp_send_handles.
|
/bot run |
|
PR_Github #17315 [ run ] triggered by Bot |
|
@reasonsolo looks like there are additional changes compared to https://github.com/NVIDIA/TensorRT-LLM/pull/6976/files. Should this target |
|
PR_Github #17315 [ run ] completed with state |
The bug says |
6 participants
Summary by CodeRabbit
New Features
Bug Fixes
Refactor
Description
The new isend/wait pattern does not degrade performance.
req/sec of llama-3.1-8B, PP=4 H100 80B PCIe (350W), ISL=1000, OSL=1000:
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.