Skip to content

[llm][docs] Document multimodal pixel-budget gotchas and vLLM compatibility#63593

Merged
eicherseiji merged 6 commits into
masterfrom
mm-data-llm-fix
Jun 8, 2026
Merged

[llm][docs] Document multimodal pixel-budget gotchas and vLLM compatibility#63593
eicherseiji merged 6 commits into
masterfrom
mm-data-llm-fix

Conversation

@jeffreywang88

@jeffreywang88 jeffreywang88 commented May 22, 2026

Copy link
Copy Markdown
Contributor

Description

  • Refine Qwen3-VL VLM video example and documentation.
Screenshot 2026-05-21 at 8 44 05 PM
  • Remove C++ incompatibility guide (only applicable for Ray 2.55).
  • Add a Ray ↔ vLLM compatibility table.
Screenshot 2026-05-21 at 8 44 35 PM
  • Update office hour link.

  • Fix a doc rendering bug

Before
Screenshot 2026-05-21 at 8 57 20 PM

After
Screenshot 2026-05-21 at 9 00 37 PM

  • Fix vLLMEngineProcessorConfig inaccurate docstring

Related issues

N/A

Additional information

Optional: Add implementation details, API changes, usage examples, screenshots, etc.

@jeffreywang88 jeffreywang88 requested a review from a team as a code owner May 22, 2026 04:01
@jeffreywang88 jeffreywang88 added the go add ONLY when ready to merge, run all tests label May 22, 2026

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Code Review

This pull request updates the VLM video examples and documentation to incorporate mm_processor_kwargs and media_io_kwargs, providing better control over video processing and frame sampling. It also introduces a vLLM compatibility table across troubleshooting guides, removes obsolete C/C++ runtime dependency information, and updates community links. Review feedback suggests aligning the num_frames parameter with the longest_edge pixel budget in the example code to avoid performance degradation from unintended downscaling, and improving documentation clarity regarding how the pixel budget affects GPU memory.

Comment thread doc/source/data/doc_code/working-with-llms/vlm_video_example.py Outdated
Comment thread doc/source/data/doc_code/working-with-llms/vlm_video_example.py Outdated
Comment thread doc/source/data/working-with-llms.rst
@ray-gardener ray-gardener Bot added serve Ray Serve Related Issue docs An issue or change related to documentation llm labels May 22, 2026
Comment thread doc/source/serve/llm/troubleshooting.md Outdated
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>

@eicherseiji eicherseiji left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

LGTM

@eicherseiji eicherseiji merged commit c936638 into master Jun 8, 2026
6 checks passed
@eicherseiji eicherseiji deleted the mm-data-llm-fix branch June 8, 2026 19:19
sampan-s-nayak pushed a commit to sampan-s-nayak/ray that referenced this pull request Jun 10, 2026
…bility (ray-project#63593)

## Description
- **Refine Qwen3-VL VLM video example and documentation.**
<img width="1293" height="408" alt="Screenshot 2026-05-21 at 8 44 05 PM"
src="https://github.com/user-attachments/assets/62bba88f-1b2b-44f6-950c-4386c0fa26fe"
/>

- **Remove C++ incompatibility guide (only applicable for Ray 2.55).**
- **Add a Ray ↔ vLLM compatibility table.**
<img width="1300" height="460" alt="Screenshot 2026-05-21 at 8 44 35 PM"
src="https://github.com/user-attachments/assets/d50c8d81-a44e-49e8-be2b-f3d5d4762b95"
/>

- **Update office hour link.**



- **Fix a doc rendering bug**

**Before**
<img width="564" height="194" alt="Screenshot 2026-05-21 at 8 57 20 PM"
src="https://github.com/user-attachments/assets/292f0b9d-86d6-4552-976f-851efa4ddb8a"
/>

**After**
<img width="533" height="198" alt="Screenshot 2026-05-21 at 9 00 37 PM"
src="https://github.com/user-attachments/assets/74243bf6-cda8-45c7-b504-ee8514a06ec4"
/>

- **Fix `vLLMEngineProcessorConfig` inaccurate docstring**

## Related issues
N/A

## Additional information
> Optional: Add implementation details, API changes, usage examples,
screenshots, etc.

---------

Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
limarkdcunha pushed a commit to limarkdcunha/ray that referenced this pull request Jun 30, 2026
…bility (ray-project#63593)

## Description
- **Refine Qwen3-VL VLM video example and documentation.**
<img width="1293" height="408" alt="Screenshot 2026-05-21 at 8 44 05 PM"
src="https://github.com/user-attachments/assets/62bba88f-1b2b-44f6-950c-4386c0fa26fe"
/>

- **Remove C++ incompatibility guide (only applicable for Ray 2.55).**
- **Add a Ray ↔ vLLM compatibility table.**
<img width="1300" height="460" alt="Screenshot 2026-05-21 at 8 44 35 PM"
src="https://github.com/user-attachments/assets/d50c8d81-a44e-49e8-be2b-f3d5d4762b95"
/>

- **Update office hour link.**



- **Fix a doc rendering bug**

**Before**
<img width="564" height="194" alt="Screenshot 2026-05-21 at 8 57 20 PM"
src="https://github.com/user-attachments/assets/292f0b9d-86d6-4552-976f-851efa4ddb8a"
/>

**After**
<img width="533" height="198" alt="Screenshot 2026-05-21 at 9 00 37 PM"
src="https://github.com/user-attachments/assets/74243bf6-cda8-45c7-b504-ee8514a06ec4"
/>

- **Fix `vLLMEngineProcessorConfig` inaccurate docstring**

## Related issues
N/A

## Additional information
> Optional: Add implementation details, API changes, usage examples,
screenshots, etc.

---------

Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

docs An issue or change related to documentation go add ONLY when ready to merge, run all tests llm serve Ray Serve Related Issue

2 participants