[TRTLLM-8263][feat] Add DSR1 and GPT-OSS Perf Tests into CI #8899
Conversation
📝 WalkthroughWalkthroughThe PR expands performance test infrastructure by introducing new configuration fields for speculative decoding, CUDA graph optimization, and backend selection. New fields are added to database utilities, server and client configuration classes, and performance test scenario definitions across three YAML files. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ 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: 2
🧹 Nitpick comments (2)
tests/integration/defs/perf/test_perf.py (2)
608-612: Consider removing redundant field initialization.These fields are unconditionally added to
db_datahere, but then conditionally added again at lines 617-628. The unconditional initialization is redundant since the conditional logic at lines 617-628 will populate these fields when appropriate.Apply this diff to remove the redundancy:
"d_free_gpu_memory_fraction": self.free_gpu_memory_fraction, "l_max_batch_size": self.max_batch_size, "l_cuda_graph_max_batch_size": self.cuda_graph_max_batch_size, "b_enable_padding": self.enable_padding, - "s_spec_decoding_type": self.spec_decoding_type, - "l_num_nextn_predict_layers": self.num_nextn_predict_layers, - "l_eagle3_layers_to_capture": self.eagle3_layers_to_capture, - "l_max_draft_len": self.max_draft_len, - "s_speculative_model_dir": self.speculative_model_dir, "s_server_log_link": "", }
756-759: Remove redundant conditional field population.The fields
s_backendandb_use_chat_templateare already unconditionally added todb_dataat lines 752-753. The conditional checks here are redundant and will simply overwrite the existing values with the same values.Apply this diff to remove the redundant code:
"b_use_chat_template": self.use_chat_template, "s_client_log_link": "", } - if self.backend: - db_data["s_backend"] = self.backend - if self.use_chat_template: - db_data["b_use_chat_template"] = self.use_chat_template return db_data
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
tests/integration/defs/perf/open_search_db_utils.py(3 hunks)tests/integration/defs/perf/test_perf.py(11 hunks)tests/scripts/perf-sanity/l0_dgx_b200.yaml(1 hunks)tests/scripts/perf-sanity/l0_dgx_gb200.yaml(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:
tests/integration/defs/perf/open_search_db_utils.pytests/integration/defs/perf/test_perf.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:
tests/integration/defs/perf/open_search_db_utils.pytests/integration/defs/perf/test_perf.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:
tests/integration/defs/perf/open_search_db_utils.pytests/integration/defs/perf/test_perf.py
🧠 Learnings (2)
📓 Common learnings
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*").
📚 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/scripts/perf-sanity/l0_dgx_gb200.yaml
🧬 Code graph analysis (1)
tests/integration/defs/perf/test_perf.py (1)
tests/scripts/perf-sanity/run_benchmark_serve.py (3)
to_cmd(278-288)to_cmd(353-367)get_model_dir(178-185)
🪛 Ruff (0.14.3)
tests/integration/defs/perf/test_perf.py
690-690: Undefined name speculative_model_dir
(F821)
722-722: Unused method argument: working_dir
(ARG002)
⏰ 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
chenfeiz0326
requested review from
chzblych,
litaotju,
venkywonka and
zeroepoch
|
/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Perf-Sanity-Post-Merge-1,DGX_B200-8_GPUs-PyTorch-Perf-Sanity-Post-Merge-1" |
|
PR_Github #23491 [ run ] triggered by Bot. Commit: |
|
/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Perf-Sanity-Post-Merge-1" |
|
PR_Github #23511 [ run ] triggered by Bot. Commit: |
|
PR_Github #23491 [ run ] completed with state |
|
PR_Github #23511 [ run ] completed with state |
|
/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Perf-Sanity-Post-Merge-1" |
|
PR_Github #23562 [ run ] triggered by Bot. Commit: |
chenfeiz0326
force-pushed
the
chenfeiz/add-dsr1-perf-testcases
branch
from
4a08799 to
7a05ee2
Compare
|
PR_Github #23562 [ run ] completed with state |
| "DGX_B300-4_GPUs-PyTorch-Post-Merge-1": ["b300-x4", "l0_dgx_b300", 1, 1, 4], | ||
| // Perf sanity post merge test | ||
| "DGX_B200-4_GPUs-PyTorch-Perf-Sanity-Post-Merge-1": ["b200-x4", "perf_sanity_l0_dgx_b200", 1, 1, 4], | ||
| "DGX_B200-8_GPUs-PyTorch-Perf-Sanity-Post-Merge-1": ["b200-x8", "perf_sanity_l0_dgx_b200", 1, 1, 8], |
There was a problem hiding this comment.
@chzblych do we have capacity to run this in L0 post-merge. I'm concerned that we're asking for 8 GPUs here rather than 4. This will basically double our requirements (going from 2x4 to an additional 1x8).
@chenfeiz0326 does this really need to run on 8 GPUs?
There was a problem hiding this comment.
There is not too much memory capacity left for DS R1 FP8 on 4 GPU, better to have 8GPUs.
|
/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Perf-Sanity-Post-Merge-1" |
|
PR_Github #23617 [ run ] triggered by Bot. Commit: |
Signed-off-by: Chenfei Zhang <[email protected]>
chenfeiz0326
force-pushed
the
chenfeiz/add-dsr1-perf-testcases
branch
from
bc25dcc to
c0a115a
Compare
|
/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Perf-Sanity-Post-Merge-1" |
|
PR_Github #23638 [ run ] triggered by Bot. Commit: |
|
PR_Github #23617 [ run ] completed with state |
|
PR_Github #23638 [ run ] completed with state |
3 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.