[https://nvbugs/5625743][test] Adding test_batch_completions_beam_sea… #9345
Conversation
…rch_streaming to cover multi-beam streaming cases required by the NIM team. Signed-off-by: SimengLiu-nv <[email protected]>
|
/bot run |
📝 WalkthroughWalkthroughA new asynchronous test function is added to validate beam search functionality with streaming for OpenAI completions. The test sends batch requests with multiple prompts and beams, streams results, and asserts consistency and distinctiveness of beam outputs. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes
Pre-merge checks and finishing touches❌ Failed checks (3 warnings)
✨ Finishing touches
🧪 Generate unit tests (beta)
Tip 📝 Customizable high-level summaries are now available in beta!You can now customize how CodeRabbit generates the high-level summary in your pull requests — including its content, structure, tone, and formatting.
Example instruction:
Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later. 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: 1
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tests/unittest/llmapi/apps/_test_openai_completions.py(1 hunks)
🧰 Additional context used
🧠 Learnings (1)
📓 Common learnings
Learnt from: moraxu
Repo: NVIDIA/TensorRT-LLM PR: 6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Learnt from: fredricz-20070104
Repo: NVIDIA/TensorRT-LLM PR: 7645
File: tests/integration/test_lists/qa/llm_function_core.txt:648-648
Timestamp: 2025-09-09T09:40:45.658Z
Learning: In TensorRT-LLM test lists, it's common and intentional for the same test to appear in multiple test list files when they serve different purposes (e.g., llm_function_core.txt for comprehensive core functionality testing and llm_function_core_sanity.txt for quick sanity checks). This duplication allows tests to be run in different testing contexts.
🧬 Code graph analysis (1)
tests/unittest/llmapi/apps/_test_openai_completions.py (1)
tensorrt_llm/_torch/pyexecutor/model_engine.py (1)
use_beam_search(517-518)
🪛 Ruff (0.14.5)
tests/unittest/llmapi/apps/_test_openai_completions.py
222-222: Comment contains ambiguous × (MULTIPLICATION SIGN). Did you mean x (LATIN SMALL LETTER X)?
(RUF003)
⏰ 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)
tests/unittest/llmapi/apps/_test_openai_completions.py (1)
207-233: LGTM! Solid test coverage for beam search streaming.The test correctly validates multi-beam streaming behavior by:
- Verifying different beams produce distinct outputs (line 229)
- Confirming identical prompts yield consistent beams across positions (lines 231-232)
- Using
temperature=0.0for deterministic, reproducible assertionsThe logic mirrors the non-streaming
test_batch_completions_beam_searchtest and aligns with the PR objectives for NIM team requirements.
| stream=True, | ||
| extra_body=dict(use_beam_search=True), | ||
| ) | ||
| texts = [""] * 4 # 2 prompts × 2 beams = 4 choices |
There was a problem hiding this comment.
Replace Unicode multiplication sign with ASCII 'x'.
The comment uses × (Unicode MULTIPLICATION SIGN) instead of ASCII x. For consistency and to avoid potential encoding issues, use the ASCII character.
Apply this diff:
- texts = [""] * 4 # 2 prompts × 2 beams = 4 choices
+ texts = [""] * 4 # 2 prompts x 2 beams = 4 choicesBased on static analysis hints.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| texts = [""] * 4 # 2 prompts × 2 beams = 4 choices | |
| texts = [""] * 4 # 2 prompts x 2 beams = 4 choices |
🧰 Tools
🪛 Ruff (0.14.5)
222-222: Comment contains ambiguous × (MULTIPLICATION SIGN). Did you mean x (LATIN SMALL LETTER X)?
(RUF003)
🤖 Prompt for AI Agents
In tests/unittest/llmapi/apps/_test_openai_completions.py around line 222, the
inline comment uses the Unicode multiplication sign '×'; replace it with the
ASCII letter 'x' so the comment reads "2 prompts × 2 beams = 4 choices" → "2
prompts x 2 beams = 4 choices" to ensure consistent ASCII encoding and avoid
potential encoding issues.
|
PR_Github #25257 [ run ] triggered by Bot. Commit: |
|
PR_Github #25257 [ run ] completed with state |
| choice = chunk.choices[0] | ||
| texts[choice.index] += choice.text | ||
|
|
||
| # Verify beam search produces different outputs for different beams |
There was a problem hiding this comment.
LGTM, however https://nvbugs/5625743 does not pass use_beam_search=True (the default is False).
So, ideally we could parametrize the test to also cover use_beam_search=False. For this case, in order not to hit this check, you could specify a very small (but non-zero) temperature. The check in L229 would need to be skipped then, since decoding is greedy-like for temperature -> 0 (unless logits are tied).
| @pytest.mark.asyncio(loop_scope="module") | ||
| @pytest.mark.parametrize("prompts", | ||
| [["Hello, my name is"] * 2, [[0, 0, 0, 0, 0]] * 2]) | ||
| async def test_batch_completions_beam_search_streaming( |
There was a problem hiding this comment.
is this test executed in pre-merge or post-merge? i'm trying to follow the logic through the nested ways to invoke tests - will this test end up calling it? https://github.com/NVIDIA/TensorRT-LLM/blob/main/tests/integration/defs/test_e2e.py#L1624
There was a problem hiding this comment.
It's on the pre-merge pipeline.
- e2e test function:
TensorRT-LLM/tests/integration/defs/test_e2e.py
Line 1588 in 32f5391
- Test list:
|
Close this pr as the NIM release will be based of release/1.1. Moving to #9471. |
4 participants
…rch_streaming to cover multi-beam streaming cases required by the NIM team.
Summary by CodeRabbit
✏️ 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.