Skip to content

Hybrid#918

Draft
liangliangchang wants to merge 3 commits into
gfx11from
hybrid
Draft

Hybrid#918
liangliangchang wants to merge 3 commits into
gfx11from
hybrid

Conversation

@liangliangchang

@liangliangchang liangliangchang commented May 4, 2026 •
edited by github-actions Bot
Loading

Copy link
Copy Markdown

Purpose

Test Plan

Test Result

Essential Elements of an Effective PR Description Checklist
  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
  • (Optional) Release notes update. If your change is user facing, please update the release notes draft in the Google Doc.

@github-actions

github-actions Bot commented May 4, 2026

Copy link
Copy Markdown

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors.

You ask your reviewers to trigger select CI tests on top of fastcheck CI.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

If you have any questions, please reach out to us on Slack at https://slack.vllm.ai.

🚀

liangliangchang and others added 2 commits June 1, 2026 15:41
@liangliangchang @cursoragent
feat: Add FlexMLRT NPU vision backend for Qwen2.5-VL
f59c1e6 
Introduce pluggable NPU vision support without scheduler or engine
pipelining changes. Vision encoding runs synchronously on the NPU when
VLLM_VISION_NPU_BACKEND=flexmlrt is set, keeping core v1 scheduling
untouched for easier upstream review.

Co-authored-by: Cursor <cursoragent@cursor.com>
@liangliangchang @cursoragent
feat: Add NPU+GPU async vision pipelining for v1 engine
988be0b 
Layer async NPU vision pre-encoding on top of the FlexMLRT backend:
vision scheduler in EngineCore, scheduler deferral when vision is not
ready, and gpu_model_runner pre-encoding thread pool. Gated by
VLLM_NPU_ASYNC_PIPELINE=1 (default off).

Co-authored-by: Cursor <cursoragent@cursor.com>
@liangliangchang @cursoragent
refactor: simplify NPU vision env and CPU preprocessor layout
8d16afa 
Use VLLM_VISION_NPU_CACHE as the sole enable switch instead of
VLLM_VISION_NPU_BACKEND. Move Qwen2.5-VL CPU preprocessing into
vision_npu/models/ and drop the unoptimized numpy path. Keep
AsyncFlexMLRTVisionBackend for pipelining when VLLM_NPU_ASYNC_PIPELINE=1.

Co-authored-by: Cursor <cursoragent@cursor.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@liangliangchang