Skip to content

test: Remove completions endpoint from vllm tests.#1575

Merged
nv-anants merged 2 commits intomainfrom
pvijayakrish/fix-vllm-tests
Jun 18, 2025
Merged

test: Remove completions endpoint from vllm tests.#1575
nv-anants merged 2 commits intomainfrom
pvijayakrish/fix-vllm-tests

Conversation

@pvijayakrish
Copy link
Copy Markdown
Contributor

@pvijayakrish pvijayakrish commented Jun 17, 2025

Overview:

Removing the completions/ endpoint from llm tests. The completions/ endpoint are expected to fail and the solution is to use dynamo run for ingress and registering endpoints.

TRTLLM, VLLM v0 and vLLM v1 are using dynamo run for ingress.

Summary by CodeRabbit

  • Tests
    • Updated test configurations to remove the "v1/completions" endpoint from several deployment graph tests. Only the "v1/chat/completions" endpoint remains tested for these cases.

Signed-off-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
Signed-off-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
@pvijayakrish pvijayakrish marked this pull request as ready for review June 18, 2025 20:41
@pvijayakrish pvijayakrish requested a review from a team June 18, 2025 20:41
@pvijayakrish pvijayakrish changed the title tests: Remove completions endpoint from vllm tests. test: Remove completions endpoint from vllm tests. Jun 18, 2025
@github-actions github-actions Bot added the test label Jun 18, 2025
@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai Bot commented Jun 18, 2025

Walkthrough

The test configurations in tests/serve/test_dynamo_serve.py were updated to remove the "v1/completions" endpoint and its corresponding response handler from several deployment graph entries. The "v1/chat/completions" endpoint and its handler remain unchanged. No other code logic or public interfaces were modified.

Changes

File(s) Change Summary
tests/serve/test_dynamo_serve.py Removed "v1/completions" endpoint and completions_response_handler from multiple graph configs

Poem

A hop, a skip, a tidy sweep,
Endpoints trimmed, no need to keep.
The chat remains, completion’s gone,
Our test graphs now are moving on.
🐇✨


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.

Copy link
Copy Markdown
Contributor

@coderabbitai coderabbitai Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

🧹 Nitpick comments (2)
tests/serve/test_dynamo_serve.py (2)

28-28: Consider cleanup: Completions response handler import may be underutilized.

After removing completions endpoints from several VLLM deployment graphs, the completions_response_handler import is now only used by sglang, vllm_v1, and tensorrt_llm deployments. While not incorrect, this reduces the utility of the import.


72-78: Consider cleanup: Completions payload definition now unused by modified deployment graphs.

The payload_completions portion of text_payload is no longer used by the VLLM deployment graphs that were modified (agg, disagg, agg_router, disagg_router, multimodal_agg), though it's still needed for other deployment types.

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between ac4fd87 and c847b7c.

📒 Files selected for processing (1)
  • tests/serve/test_dynamo_serve.py (5 hunks)
🔇 Additional comments (6)
tests/serve/test_dynamo_serve.py (6)

90-93: LGTM: Completions endpoint correctly removed for VLLM agg deployment.

The change aligns with the PR objective to remove failing completions endpoints from VLLM tests. The endpoints and response_handlers lists remain properly synchronized.


117-120: LGTM: Completions endpoint correctly removed for VLLM disagg deployment.

Consistent with the agg deployment change, maintaining proper alignment between endpoints and handlers.


130-133: LGTM: Completions endpoint correctly removed for VLLM agg_router deployment.

The change maintains consistency across VLLM deployment variants.


147-150: LGTM: Completions endpoint correctly removed for VLLM disagg_router deployment.

Consistent application of the completions endpoint removal for VLLM deployments.


164-167: LGTM: Completions endpoint correctly removed for multimodal VLLM deployment.

The multimodal deployment configuration correctly follows the same pattern as other VLLM deployments.


84-250: Verify selective application aligns with deployment capabilities.

The changes target only VLLM deployment graphs while preserving completions endpoints for sglang, vllm_v1, and tensorrt_llm deployments. Ensure this selective approach matches the actual endpoint support capabilities of these different LLM backends.

#!/bin/bash
# Description: Verify that the deployment graphs still retaining completions endpoints actually support them
# Expected: Find evidence that sglang, vllm_v1, and tensorrt_llm configs support completions endpoint

echo "=== Checking configuration files for completions endpoint support ==="
echo "VLLM configs (should not mention completions after this change):"
fd -e yaml . "/workspace/examples/llm/configs" --exec cat {} \; 2>/dev/null || echo "VLLM configs not found"

echo -e "\nSGLang configs (should support completions):"
fd -e yaml . "/workspace/examples/sglang/configs" --exec cat {} \; 2>/dev/null || echo "SGLang configs not found"

echo -e "\nVLLM v1 configs (should support completions):"
fd -e yaml . "/workspace/examples/vllm_v1/configs" --exec cat {} \; 2>/dev/null || echo "VLLM v1 configs not found"

echo -e "\nTensorRT-LLM configs (should support completions):"
fd -e yaml . "/workspace/examples/tensorrt_llm/configs" --exec cat {} \; 2>/dev/null || echo "TensorRT-LLM configs not found"

@nv-anants nv-anants merged commit e7cfe0f into main Jun 18, 2025
11 of 13 checks passed
@nv-anants nv-anants deleted the pvijayakrish/fix-vllm-tests branch June 18, 2025 21:15
pvijayakrish added a commit that referenced this pull request Jun 24, 2025
Signed-off-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
nv-anants pushed a commit that referenced this pull request Jun 24, 2025
Signed-off-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
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.

3 participants