[None][feat] Run extra general warmup to warm up memory pool #10340
Conversation
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
|
/bot run |
📝 WalkthroughWalkthroughAdds conditional warmup logic to ModelEngine that executes a general memory pool warmup when KV cache is not estimating. Introduces a new Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
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: 0
🧹 Nitpick comments (1)
tensorrt_llm/_torch/pyexecutor/model_engine.py (1)
574-604: New general warmup after CUDA graph capture looks correct; consider resettingenable_spec_decodebefore running itThe added block:
self._run_torch_compile_warmup(resource_manager) self._run_autotuner_warmup(resource_manager) self._run_cuda_graph_warmup(resource_manager) if not kv_cache_manager.is_estimating_kv_cache: # Run extra general warmup to warmup memory pool before run real requests. self._general_warmup(resource_manager, reverse=True) # Set the value back to the original value after all warmups are complete self.enable_spec_decode = self.is_spec_decodereuses the existing
_general_warmuphelper and correctly avoids doing a heavy general warmup in KV‑cache estimation mode. Running it withreverse=True(largest shapes first) also makes sense for priming the allocator/memory pool.One nuance:
_run_cuda_graph_warmup()can leaveself.enable_spec_decodein a state that reflects the lastdraft_lenused for CUDA graph capture, which may differ fromself.is_spec_decode. Because_general_warmup()usesself.runtime_draft_len(derived fromself.enable_spec_decode) to size dummy requests, the general warmup may not exactly match the final runtime speculative mode.If you want general warmup to reflect the “real” runtime mode, consider restoring
enable_spec_decodebefore calling_general_warmup:Suggested ordering tweak (optional)
- self._run_torch_compile_warmup(resource_manager) - self._run_autotuner_warmup(resource_manager) - self._run_cuda_graph_warmup(resource_manager) - if not kv_cache_manager.is_estimating_kv_cache: - # Run extra general warmup to warmup memory pool before run real requests. - self._general_warmup(resource_manager, reverse=True) - - # Set the value back to the original value after all warmups are complete - self.enable_spec_decode = self.is_spec_decode + self._run_torch_compile_warmup(resource_manager) + self._run_autotuner_warmup(resource_manager) + self._run_cuda_graph_warmup(resource_manager) + + # Restore runtime speculative-decoding mode before general warmup. + # This ensures _general_warmup sees the same enable_spec_decode + # setting that real requests will use. + self.enable_spec_decode = self.is_spec_decode + + if not kv_cache_manager.is_estimating_kv_cache: + # Run extra general warmup to warm up memory pools before real requests. + self._general_warmup(resource_manager, reverse=True)Functionally this is a small behavioral tweak; the current code is still safe, as earlier warmup steps already exercise both speculative and non‑speculative shapes where applicable.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tensorrt_llm/_torch/pyexecutor/model_engine.pytensorrt_llm/_torch/pyexecutor/resource_manager.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/model_engine.pytensorrt_llm/_torch/pyexecutor/resource_manager.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/model_engine.pytensorrt_llm/_torch/pyexecutor/resource_manager.py
🧠 Learnings (1)
📚 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/model_engine.pytensorrt_llm/_torch/pyexecutor/resource_manager.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/resource_manager.py (1)
178-199: Exposeis_estimating_kv_cacheon KVCacheManager instanceStoring the constructor flag on
self.is_estimating_kv_cachealigns with how the rest of the engine introspects manager state (and matches the new usage inModelEngine.warmup). No behavioral issues here; this is a straightforward, low‑risk change.
|
PR_Github #30161 [ run ] triggered by Bot. Commit: |
|
PR_Github #30161 [ run ] completed with state
|
| self._run_autotuner_warmup(resource_manager) | ||
| self._run_cuda_graph_warmup(resource_manager) | ||
| if not kv_cache_manager.is_estimating_kv_cache: | ||
| # Run extra general warmup to warmup memory pool before run real requests. |
There was a problem hiding this comment.
nit: before run -> before running
3 participants
Summary by CodeRabbit
Release Notes
✏️ Tip: You can customize this high-level summary in your review settings.
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
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 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.