Skip to content

Conversation

@ptarasiewiczNV
Copy link
Contributor

@ptarasiewiczNV ptarasiewiczNV commented Jul 22, 2025

Overview:

To enable using --fixed-schedule triton-inference-server/perf_analyzer#366
to avoid repeating samples in the warmup and profiling which results in unexpected cache hits.

Details:

Where should the reviewer start?

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

  • closes GitHub issue: #xxx

Summary by CodeRabbit

  • Chores
    • Updated the version of the genai-perf package to 0.0.15.

@copy-pr-bot
Copy link

copy-pr-bot bot commented Jul 22, 2025

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@github-actions github-actions bot added the chore label Jul 22, 2025
@ptarasiewiczNV ptarasiewiczNV enabled auto-merge (squash) July 22, 2025 18:01
@ptarasiewiczNV
Copy link
Contributor Author

/ok to test 2748d06

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Jul 22, 2025

Walkthrough

The version of the genai-perf package in the container/deps/requirements.txt file was updated from 0.0.13 to 0.0.15. No other dependencies were modified.

Changes

File(s) Change Summary
container/deps/requirements.txt Updated genai-perf version from 0.0.13 to 0.0.15.

Estimated code review effort

1 (~2 minutes)

Poem

A bunny hopped with gentle cheer,
To bump a version—never fear!
From thirteen up to fifteen high,
Dependencies now reach the sky.
With paws that type and ears that perk,
The code is ready—back to work!
🐇✨


📜 Recent review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between d65ce1b and 2748d06.

📒 Files selected for processing (1)
  • container/deps/requirements.txt (1 hunks)
⏰ 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: Build and Test - vllm
🔇 Additional comments (1)
container/deps/requirements.txt (1)

20-20: Unable to verify automatically – please manually confirm genai-perf and perf_analyzer compatibility

The sandbox environment is missing system dependencies (e.g., libsndfile) and the perf_analyzer binary, so we can’t auto-check the new --fixed-schedule flag or the analyzer version here. Please verify the following in your container image:

  • Confirm genai-perf --help lists the --fixed-schedule flag.
  • Ensure the Triton perf_analyzer binary is installed and at version ≥ 1.36, or the new flag will error at runtime.
  • Refresh any pinned lockfiles (e.g., requirements.txt.freeze, poetry.lock, pip-compile outputs) so hashes stay in sync.
  • Run your perf smoke tests to ensure JSON output is stable in 0.0.15 (0.0.14 had a brief breaking change).

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.
    • Explain this complex logic.
    • 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. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • 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 src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need 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)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

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 anywhere in the PR title to generate the title automatically.

Documentation and Community

  • 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
Copy link
Contributor

coderabbitai bot commented Jul 22, 2025

Walkthrough

The version of the genai-perf package in the requirements file was updated from 0.0.13 to 0.0.15. No other dependencies were altered.

Changes

File(s) Change Summary
container/deps/requirements.txt Updated genai-perf version from 0.0.13 to 0.0.15

Estimated code review effort

1 (~2 minutes)

Poem

In the garden of code, a seed was sown,
A version bumped, a package grown.
From thirteen to fifteen, the numbers climb,
Dependencies freshened, right on time!
🐇✨


📜 Recent review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between d65ce1b and 2748d06.

📒 Files selected for processing (1)
  • container/deps/requirements.txt (1 hunks)
⏰ 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: Build and Test - vllm
🔇 Additional comments (1)
container/deps/requirements.txt (1)

20-20: Verify genai-perf v0.0.15 compatibility
No public changelog is available for v0.0.15, so please manually confirm that neither the CLI options nor any Python APIs used in our codebase have changed in a way that could break existing workflows.

Key places to sanity-check against v0.0.15:

  • examples/router_standalone/perf.sh (line 31)
  • deploy/sdk/src/dynamo/sdk/cli/env.py (import at line 109)
  • benchmarks/profiler/utils/genai_perf.py (_get_common_genai_perf_cmd, get_prefill_genai_perf_cmd, get_decode_genai_perf_cmd)
  • benchmarks/llm/plot_pareto.py (parsing of profile_export_genai_perf.json)

Actions:

  • Run the existing examples and CI-covered scripts that invoke genai-perf profile …
  • Verify that all options (e.g., --tokenizer, --service-kind, --streaming, etc.) still work as expected
  • Ensure generated JSON schema hasn’t changed in a breaking way

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.
    • Explain this complex logic.
    • 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. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • 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 src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need 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)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

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 anywhere in the PR title to generate the title automatically.

Documentation and Community

  • 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.

@ptarasiewiczNV ptarasiewiczNV merged commit 9cfaa7b into main Jul 22, 2025
6 checks passed
@ptarasiewiczNV ptarasiewiczNV deleted the ptarasiewicz/bump-genai-perf-0.0.15 branch July 22, 2025 20:20
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants