[None][test] rename test case and add fallback for multinode cases#13537
[None][test] rename test case and add fallback for multinode cases#13537ruodil merged 3 commits intoNVIDIA:mainfrom
Conversation
📝 WalkthroughWalkthroughThis pull request updates performance test infrastructure to use MiniMax M2.5 FP8 precision model variant instead of BF16, and modifies GPU availability validation in test configuration to support multi-node SLURM cluster setups by computing total GPUs across all nodes. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes 🚥 Pre-merge checks | ✅ 3 | ❌ 2❌ Failed checks (1 warning, 1 inconclusive)
✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
tests/integration/defs/perf/test_perf.py (1)
1-1:⚠️ Potential issue | 🟠 MajorUpdate the SPDX copyright year for this modified Python file.
Line 1 still ends at 2025, but this file is modified in 2026 and should be updated accordingly.
Proposed fix
-# SPDX-FileCopyrightText: Copyright (c) 2022-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# SPDX-FileCopyrightText: Copyright (c) 2022-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.As per coding guidelines: "Include NVIDIA copyright header on all new files; update year on modified files".
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@tests/integration/defs/perf/test_perf.py` at line 1, Update the SPDX copyright year in the file header: change the top-of-file SPDX comment that currently ends with "2025" to "2026" so the modified Python file reflects the correct copyright year; locate the SPDX line at the very top of the file (the SPDX-FileCopyrightText comment) and edit the year range accordingly.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@tests/integration/test_lists/qa/llm_perf_core.yml`:
- Around line 227-234: The QA perf list added multiple minimax_m2.5_fp8 test
entries (e.g.
perf/test_perf.py::test_perf[minimax_m2.5_fp8-bench-pytorch-float8-...]) but the
authoritative pre-merge CI list (l0_perf) was not updated; add the same
minimax_m2.5_fp8 entries present in qa/ (all variants shown in the diff:
different input_output_len, maxbs, reqs, con, tp/gpus) into the l0_perf.yml
test-db list so the tests run in pre-merge CI, ensuring the exact test
identifiers are copied so CI picks them up.
---
Outside diff comments:
In `@tests/integration/defs/perf/test_perf.py`:
- Line 1: Update the SPDX copyright year in the file header: change the
top-of-file SPDX comment that currently ends with "2025" to "2026" so the
modified Python file reflects the correct copyright year; locate the SPDX line
at the very top of the file (the SPDX-FileCopyrightText comment) and edit the
year range accordingly.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: a8054059-6ffe-4ae4-9d2b-ee266925a70c
📒 Files selected for processing (2)
tests/integration/defs/perf/test_perf.pytests/integration/test_lists/qa/llm_perf_core.yml
|
/bot run |
|
PR_Github #45892 [ run ] triggered by Bot. Commit: |
|
PR_Github #45892 [ run ] completed with state
|
ruodil
force-pushed
the
user/ruodil/perf
branch
from
c391358 to
a594f58
Compare
|
/bot run |
|
PR_Github #46279 [ run ] triggered by Bot. Commit: |
|
PR_Github #46279 [ run ] completed with state |
Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
GLM-5 tokenizer_config.json sets tokenizer_class=TokenizersBackend which AutoTokenizer cannot import without trust_remote_code=True, causing trtllm-bench prepare-dataset to fail with a pydantic ValidationError for all glm_5_fp8 perf cases. Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com>
|
/bot --reuse-pipeline |
GitHub Bot Help
Provide a user friendly way for developers to interact with a Jenkins server. Run See details below for each supported subcommand. Details
Launch build/test pipelines. All previously running jobs will be killed.
kill
Kill all running builds associated with pull request. skip
Skip testing for latest commit on pull request. reuse-pipeline
Reuse 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. |
|
/bot reuse-pipeline |
|
PR_Github #46729 [ reuse-pipeline ] triggered by Bot. Commit: |
|
PR_Github #46729 [ reuse-pipeline ] completed with state |
5 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
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
To see a list of available CI bot commands, please comment
/bot help.