[https://nvbugs/5436461][fix] Adjust free_gpu_memory_fraction of test_eagle3 #7673

leslie-fang25 · 2025-09-10T10:07:14Z

Summary by CodeRabbit

New Features
- Added an option to control GPU memory usage during KV cache operations via a configurable free GPU memory fraction.
- Extended cache configuration to support finer control without requiring block reuse changes.
Tests
- Enabled previously skipped accuracy tests on devices with limited memory.
- Updated test configurations to reflect the new GPU memory fraction setting.

Description

Cherry pick #6631 for https://nvbugspro.nvidia.com/bug/5436461 into 1.0 release branch.

Test Coverage

python -u -m pytest -s -v  accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3

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.

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 the stage-list parameter 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.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip 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-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.

…_eagle3 Signed-off-by: leslie-fang25 <leslief@nvidia.com>

coderabbitai · 2025-09-10T10:07:22Z

📝 Walkthrough

Walkthrough

Removed memory-based skip decorators from two tests and updated KvCacheConfig usage within tests to include free_gpu_memory_fraction=0.6 alongside enable_block_reuse=False.

Changes

Cohort / File(s)	Summary
Integration tests: KV cache config and skip removal `tests/integration/defs/accuracy/test_llm_api_pytorch.py`	- Removed memory-based skip from test_eagle3 in TestQwen3_8B and TestQwen3_30B_A3B - Updated KvCacheConfig calls to include free_gpu_memory_fraction=0.6 - Reflects KvCacheConfig constructor now accepting free_gpu_memory_fraction

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Tip

👮 Agentic pre-merge checks are now available in preview!

Pro plan users can now enable pre-merge checks in their settings to enforce checklists before merging PRs.

Built-in checks – Quickly apply ready-made checks to enforce title conventions, require pull request descriptions that follow templates, validate linked issues for compliance, and more.
Custom agentic checks – Define your own rules using CodeRabbit’s advanced agentic capabilities to enforce organization-specific policies and workflows. For example, you can instruct CodeRabbit’s agent to verify that API documentation is updated whenever API schema files are modified in a PR. Note: Upto 5 custom checks are currently allowed during the preview period. Pricing for this feature will be announced in a few weeks.

Please see the documentation for more information.

Example:

reviews:
  pre_merge_checks:
    custom_checks:
      - name: "Undocumented Breaking Changes"
        mode: "warning"
        instructions: |
          Pass/fail criteria: All breaking changes to public APIs, CLI flags, environment variables, configuration keys, database schemas, or HTTP/GraphQL endpoints must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md. Exclude purely internal or private changes (e.g., code not exported from package entry points or explicitly marked as internal).

Please share your feedback with us on this Discord post.

Pre-merge checks (1 passed, 2 warnings)

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run `@coderabbitai generate docstrings` to improve docstring coverage.
Description Check	⚠️ Warning	The PR description retains the commented-out title template and does not include a properly formatted title line matching [JIRA ticket/NVBugs ID/GitHub issue/None][type] Summary, nor does it include the required `@coderabbitai summary` header. While it has Description, Test Coverage, and Checklist sections, it fails to replace placeholders with actual content or explain the change rationale in the prescribed template structure. These omissions mean the PR description does not adhere to the repository’s required template.	Please add a properly formatted title line (for example, [https://nvbugs/5436461][fix] Adjust free_gpu_memory_fraction of test_eagle3), include the `@coderabbitai summary` header or an explicit summary at the top, remove all placeholder comments, and ensure the Description and Test Coverage sections contain the actual details and tests relevant to this change.

✅ Passed checks (1 passed)

Check name	Status	Explanation
Title Check	✅ Passed	The title “[https://nvbugs/5436461][fix] Adjust free_gpu_memory_fraction of test_eagle3” follows the project’s naming conventions by including the NVBugs ID and the [fix] type, and it concisely summarizes the key change to the test_eagle3 configuration without extraneous details. It is specific, clear, and aligns with the expected format.

✨ Finishing Touches

📝 Generate Docstrings

🧪 Generate unit tests

Create PR with unit tests
Post copyable unit tests in a comment

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.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

leslie-fang25 · 2025-09-10T10:13:15Z

/bot run

HuiGao-NV

LGTM

coderabbitai

Actionable comments posted: 0

🧹 Nitpick comments (1)

tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)

2067-2070: Make the 0.6 fraction overrideable via env to de-flake across lab hardware.

Different CI runners/driver stacks may still OOM or underutilize. Allow an env override with a brief comment.

Apply:

-        kv_cache_config = KvCacheConfig(
-            enable_block_reuse=False,
-            free_gpu_memory_fraction=0.6,
-        )
+        # Tuneable for CI/hardware variance; default 60% avoids OOM while reuse stays off for Eagle3.
+        mem_frac = float(os.getenv("TRTLLM_FREE_GPU_MEM_FRAC_EAGLE3_QWEN3_8B", "0.6"))
+        kv_cache_config = KvCacheConfig(
+            enable_block_reuse=False,
+            free_gpu_memory_fraction=mem_frac,
+        )

📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 7c2f04f and 5c55ee3.

📒 Files selected for processing (1)

tests/integration/defs/accuracy/test_llm_api_pytorch.py (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/accuracy/test_llm_api_pytorch.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/accuracy/test_llm_api_pytorch.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/accuracy/test_llm_api_pytorch.py

🧬 Code graph analysis (1)

tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)

tensorrt_llm/llmapi/llm_args.py (1)

KvCacheConfig (923-1002)

⏰ 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 (2)

tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)

2067-2070: Free-GPU-memory fraction set to 0.6 is a sensible, low-risk fix to unskip Eagle3 on 8B.

This targets KV cache pressure without altering execution paths. Looks consistent with other tests using 0.5–0.9.

2067-2070: Run the updated test with the correct path
python -u -m pytest -s -v tests/integration/defs/accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_eagle3

tensorrt-cicd · 2025-09-10T10:18:31Z

PR_Github #18361 [ run ] triggered by Bot

tensorrt-cicd · 2025-09-10T12:51:39Z

PR_Github #18361 [ run ] completed with state SUCCESS
/LLM/release-1.0/L0_MergeRequest_PR pipeline #372 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

leslie-fang25 · 2025-09-10T13:12:51Z

@NVIDIA/trt-llm-release-branch-approval please kindly take a look

…_eagle3 (NVIDIA#7673) Signed-off-by: leslie-fang25 <leslief@nvidia.com>

…_eagle3 (NVIDIA#7673) Signed-off-by: leslie-fang25 <leslief@nvidia.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

[https://nvbugs/5436461][fix] Adjust free_gpu_memory_fraction of test…

5c55ee3

…_eagle3 Signed-off-by: leslie-fang25 <leslief@nvidia.com>

leslie-fang25 requested a review from a team as a code owner September 10, 2025 10:07

leslie-fang25 requested a review from HuiGao-NV September 10, 2025 10:13

HuiGao-NV approved these changes Sep 10, 2025

View reviewed changes

coderabbitai bot reviewed Sep 10, 2025

View reviewed changes

chzblych approved these changes Sep 10, 2025

View reviewed changes

chzblych merged commit 9ca8662 into NVIDIA:release/1.0 Sep 10, 2025
7 checks passed

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 15, 2025

[https://nvbugs/5436461][fix] Adjust free_gpu_memory_fraction of test…

2751822

…_eagle3 (NVIDIA#7673) Signed-off-by: leslie-fang25 <leslief@nvidia.com>

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[https://nvbugs/5436461][fix] Adjust free_gpu_memory_fraction of test_eagle3 #7673

[https://nvbugs/5436461][fix] Adjust free_gpu_memory_fraction of test_eagle3 #7673

Uh oh!

leslie-fang25 commented Sep 10, 2025 •

edited

Loading

Uh oh!

coderabbitai bot commented Sep 10, 2025 •

edited

Loading

Walkthrough

Changes

Estimated code review effort

Uh oh!

leslie-fang25 commented Sep 10, 2025

Uh oh!

HuiGao-NV left a comment

Uh oh!

coderabbitai bot left a comment

Uh oh!

tensorrt-cicd commented Sep 10, 2025

Uh oh!

tensorrt-cicd commented Sep 10, 2025

Uh oh!

leslie-fang25 commented Sep 10, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

[https://nvbugs/5436461][fix] Adjust free_gpu_memory_fraction of test_eagle3 #7673

[https://nvbugs/5436461][fix] Adjust free_gpu_memory_fraction of test_eagle3 #7673

Uh oh!

Conversation

leslie-fang25 commented Sep 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

coderabbitai bot commented Sep 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Pre-merge checks (1 passed, 2 warnings)

Uh oh!

leslie-fang25 commented Sep 10, 2025

Uh oh!

HuiGao-NV left a comment

Choose a reason for hiding this comment

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

tensorrt-cicd commented Sep 10, 2025

Uh oh!

tensorrt-cicd commented Sep 10, 2025

Uh oh!

leslie-fang25 commented Sep 10, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

leslie-fang25 commented Sep 10, 2025 •

edited

Loading

coderabbitai bot commented Sep 10, 2025 •

edited

Loading