[https://nvbugs/5449218][fix] Fix KvCacheConfig error in test_perf #6937

peaceh-nv · 2025-08-15T07:15:48Z

Summary by CodeRabbit

Tests
- Updated performance test model configuration to use dictionary-based cache settings, aligning configuration structure and reducing internal dependencies. This simplifies customizing cache options during test runs, improves consistency across configurations, and enhances maintainability of the test suite. No changes to runtime behavior or user-facing features; all adjustments are confined to testing scaffolding and validation workflows.

Description

Use dict instead of object for kv cache config

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 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.

Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>

coderabbitai · 2025-08-15T07:15:55Z

📝 Walkthrough

Walkthrough

Adjusted kv_cache_config handling in tests/integration/defs/perf/pytorch_model_config.py by removing KvCacheConfig import, defaulting kv_cache_config to a dict, and updating dtype handling to use dict keys. Returned base_config now contains kv_cache_config as a plain dict instead of a KvCacheConfig instance.

Changes

Cohort / File(s)	Summary of Changes
PyTorch perf test config `tests/integration/defs/perf/pytorch_model_config.py`	Removed `KvCacheConfig` import; changed default `kv_cache_config` from `KvCacheConfig()` to `{}`; updated `kv_cache_dtype` handling to set `kv_cache_config['dtype']`; merged dict-based `kv_cache_config` into `base_config`.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~7 minutes

Possibly related PRs

[fix] Fixes KV Cache overrides in trtllm-bench #6103 — Similar refactor to represent and merge kv_cache_config as a dict rather than a KvCacheConfig object.

Suggested reviewers

yilin-void
zbpatel
Shixiaowei02
StanleySun639
LarryXFly

Tip

🔌 Remote MCP (Model Context Protocol) integration is now available!

Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats.

✨ 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

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

Review comments: Directly reply to a review comment made by CodeRabbit. Example:
- I pushed a fix in commit <commit_id>, please review it.
- Open a follow-up GitHub issue for this discussion.
Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query.
PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
- @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR/Issue comments)

Type @coderabbitai help to get the list of available commands.

Other keywords and placeholders

Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
Add @coderabbitai or @coderabbitai title anywhere in the PR title to generate the title automatically.

Status, Documentation and Community

Visit our Status Page to check the current availability of CodeRabbit.
Visit our Documentation for detailed information on how to use CodeRabbit.
Join our Discord Community to get help, request features, and share feedback.
Follow us on X/Twitter for updates and announcements.

coderabbitai

Actionable comments posted: 1

🧹 Nitpick comments (2)

tests/integration/defs/perf/pytorch_model_config.py (2)
203-207: Minor simplification: use setdefault and avoid the extra update.

Slightly tighter and clearer, with identical behavior.

Apply:
-    kv_cache_config = base_config.get('kv_cache_config', {})
-    if 'kv_cache_dtype' in base_config:
-        kv_cache_dtype = base_config.pop('kv_cache_dtype', 'auto')
-        kv_cache_config['dtype'] = kv_cache_dtype
-        base_config.update({'kv_cache_config': kv_cache_config})
+    kv_cache_config = base_config.setdefault('kv_cache_config', {})
+    if 'kv_cache_dtype' in base_config:
+        kv_cache_config['dtype'] = base_config.pop('kv_cache_dtype', 'auto')
30-31: Python 3.8 compatibility: list[str] requires 3.9+.

Per repo guidelines (Python 3.8+), either enable postponed annotations or use typing.List/Optional.

Option A (minimal): add future import (after module docstring, before any other code):
from __future__ import annotations
Option B: switch to typing aliases in the signature:
- def get_model_yaml_config(model_label: str,
-                           lora_dirs: list[str] = None) -> dict:
+ def get_model_yaml_config(model_label: str,
+                           lora_dirs: Optional[List[str]] = None) -> dict:
And add (near the top of the module):
from typing import List, Optional

📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

💡 Knowledge Base configuration:

MCP integration is disabled by default for public repositories
Jira integration is disabled by default for public repositories
Linear integration is disabled by default for public repositories

You can enable these sources in your CodeRabbit configuration.

📥 Commits

Reviewing files that changed from the base of the PR and between 96be46f and 1e520bc.

📒 Files selected for processing (1)

tests/integration/defs/perf/pytorch_model_config.py (1 hunks)

🧰 Additional context used

📓 Path-based instructions (2)

**/*.py

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

**/*.py: Python code must target Python 3.8+
Python indentation: 4 spaces, no tabs
Maintain module namespace in imports (from package.subpackage import foo; then use foo.SomeClass())
Python file names use snake_case
Python class names use PascalCase
Python functions/methods and local variables use snake_case; variables starting with a number get k_ prefix (e.g., k_99th_percentile)
Global variables use G_ prefixed UPPER_SNAKE_CASE (e.g., G_MY_GLOBAL)
Constants use UPPER_SNAKE_CASE in Python
Avoid shadowing variables from outer scopes in Python
Initialize all externally visible members of a Python class in init
Prefer docstrings for interfaces used outside a file; comments for local code
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes/variables inline with short docstrings
Avoid reflection when simple alternatives exist (e.g., prefer explicit parameters over dict(**locals()))
In try/except, catch the narrowest exceptions possible
For duck-typing with try/except, keep try body minimal and put logic in else

Files:

tests/integration/defs/perf/pytorch_model_config.py

**/*.{cpp,cxx,cc,cu,h,hpp,hxx,hh,cuh,py}

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

Prepend NVIDIA copyright header (current year) to all source files

Files:

tests/integration/defs/perf/pytorch_model_config.py

🔇 Additional comments (1)

tests/integration/defs/perf/pytorch_model_config.py (1)

203-207: LGTM: dict-based kv_cache_config fixes the test_perf KvCacheConfig error and removes the type coupling.

Switching to a plain dict, popping kv_cache_dtype, and wiring it under kv_cache_config['dtype'] is a clean, targeted fix that aligns with the PR goal. The flow is safe given base_config’s construction in this function.

tests/integration/defs/perf/pytorch_model_config.py

peaceh-nv · 2025-08-15T07:48:04Z

/bot run

tensorrt-cicd · 2025-08-15T07:54:11Z

PR_Github #15418 [ run ] triggered by Bot

tensorrt-cicd · 2025-08-15T15:22:56Z

PR_Github #15418 [ run ] completed with state FAILURE
/LLM/release-1.0/L0_MergeRequest_PR pipeline #138 completed with status: 'FAILURE'

peaceh-nv · 2025-08-18T01:49:53Z

/bot run

tensorrt-cicd · 2025-08-18T01:55:21Z

PR_Github #15562 [ run ] triggered by Bot

tensorrt-cicd · 2025-08-18T04:40:23Z

PR_Github #15562 [ run ] completed with state SUCCESS
/LLM/release-1.0/L0_MergeRequest_PR pipeline #167 completed with status: 'SUCCESS'

Superjomn

LGTM

…VIDIA#6937) Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>

…VIDIA#6937) Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

…6937) Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

[https://nvbugs/5449218][fix]: Fix KvCacheConfig error in test_perf

1e520bc

Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>

peaceh-nv requested a review from a team as a code owner August 15, 2025 07:15

peaceh-nv requested a review from Superjomn August 15, 2025 07:16

coderabbitai bot reviewed Aug 15, 2025

View reviewed changes

tests/integration/defs/perf/pytorch_model_config.py Show resolved Hide resolved

peaceh-nv changed the title ~~[https://nvbugs/5449218][fix]: Fix KvCacheConfig error in test_perf~~ [https://nvbugs/5449218][fix] Fix KvCacheConfig error in test_perf Aug 15, 2025

Superjomn approved these changes Aug 18, 2025

View reviewed changes

Superjomn requested a review from litaotju August 18, 2025 07:21

litaotju approved these changes Aug 18, 2025

View reviewed changes

litaotju merged commit 28526fe into NVIDIA:release/1.0 Aug 18, 2025
4 of 6 checks passed

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Aug 22, 2025

[https://nvbugs/5449218][fix] Fix KvCacheConfig error in test_perf (N…

261fb6d

…VIDIA#6937) Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com>

coderabbitai bot mentioned this pull request Aug 29, 2025

[https://nvbugs/5448767][fix] disable kv cache reuse for disagg pp>1 tests #7354

Merged

1 task

[https://nvbugs/5449218][fix] Fix KvCacheConfig error in test_perf #6937

[https://nvbugs/5449218][fix] Fix KvCacheConfig error in test_perf #6937

Uh oh!

Conversation

peaceh-nv commented Aug 15, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

coderabbitai bot commented Aug 15, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested reviewers

Chat

Support

CodeRabbit Commands (Invoked using PR/Issue comments)

Other keywords and placeholders

Status, Documentation and Community

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

peaceh-nv commented Aug 15, 2025

Uh oh!

tensorrt-cicd commented Aug 15, 2025

Uh oh!

tensorrt-cicd commented Aug 15, 2025

Uh oh!

peaceh-nv commented Aug 18, 2025

Uh oh!

tensorrt-cicd commented Aug 18, 2025

Uh oh!

tensorrt-cicd commented Aug 18, 2025

Uh oh!

Superjomn left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

peaceh-nv commented Aug 15, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Aug 15, 2025 •

edited

Loading