Add Acceptance Rate calculation to benchmark_serving #6240
Conversation
|
""" WalkthroughA new integer field, Changes
Estimated code review effort2 (~20 minutes) Poem
📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (2)
⏰ 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)
✨ Finishing Touches
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
|
/bot run |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tensorrt_llm/serve/scripts/backend_request_func.py(11 hunks)tensorrt_llm/serve/scripts/benchmark_serving.py(9 hunks)
🪛 Ruff (0.12.2)
tensorrt_llm/serve/scripts/benchmark_serving.py
480-480: Line too long (132 > 120)
(E501)
🧰 Additional context used
🪛 Ruff (0.12.2)
tensorrt_llm/serve/scripts/benchmark_serving.py
480-480: Line too long (132 > 120)
(E501)
⏰ 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 (8)
tensorrt_llm/serve/scripts/backend_request_func.py (3)
47-47: LGTM: Clean addition of decode_iteration field.The new field is well-documented, properly typed, and has a sensible default value.
180-180: LGTM: Well-implemented decode_iteration tracking.This implementation correctly:
- Increments only when actual text content is received (line 218)
- Uses
output_tokensfor non-streaming estimation, which is more accurate than word count- Provides consistent fallback behavior
This approach is better than the TRT-LLM implementation.
Also applies to: 217-220, 234-234, 245-246
323-323: LGTM: Consistent implementation with OpenAI completions.The decode_iteration tracking follows the same solid pattern as the completions function:
- Conditional increment for actual content
- Proper use of
output_tokensfor non-streaming estimation- Consistent behavior across OpenAI-compatible endpoints
Also applies to: 354-357, 366-366, 376-377
tensorrt_llm/serve/scripts/benchmark_serving.py (5)
80-84: LGTM: Well-structured addition of request_ar metrics to dataclass.The new fields follow existing naming conventions and are properly typed. The integration is clean and consistent with other metrics.
248-252: LGTM: Consistent metrics calculation for request_ar.The metrics calculation follows the established pattern and properly handles edge cases with the
or 0fallback.
456-459: LGTM: Consistent reporting of request_ar metrics.The console output and result dictionary updates follow established patterns and maintain consistency with other metrics.
Also applies to: 472-473
571-572: LGTM: Consistent updates to save functionality.The save functions properly include request_ar summary metrics while correctly excluding raw arrays when detailed saving is disabled. The implementation maintains consistency across both save functions.
Also applies to: 576-576, 800-801
1001-1005: LGTM: Appropriate CLI updates for request_ar metric.The CLI argument updates properly include request_ar in the default percentile metrics and update the help text accordingly. The changes maintain consistency with the existing argument structure.
zerollzeng
changed the title
|
PR_Github #12497 [ run ] triggered by Bot |
|
PR_Github #12497 [ run ] completed with state |
zerollzeng
force-pushed
the
request-ar
branch
2 times, most recently
from
d7b0098 to
e3eaf1a
Compare
|
/bot run |
|
PR_Github #12529 [ run ] triggered by Bot |
|
PR_Github #12529 [ run ] completed with state |
Signed-off-by: Zero Zeng <[email protected]>
|
/bot run |
|
PR_Github #12535 [ run ] triggered by Bot |
|
PR_Github #12535 [ run ] completed with state |
|
/bot run |
|
PR_Github #12632 [ run ] triggered by Bot |
|
PR_Github #12632 [ run ] completed with state |
Summary by CodeRabbit
New Features
Enhancements
Description
Test Coverage
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.