Skip to content

Pull requests: vllm-project/vllm-omni

New pull request New
27 Open 133 Closed
27 Open 133 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Model] Fuse Z-Image's qkv_proj and gate_up_proj
#226 opened Dec 6, 2025 by Isotr0py Loading…
1 of 5 tasks
2
[Docs] Add basic usage examples for diffusion documentation Improvements or additions to documentation
#222 opened Dec 6, 2025 by SamitHuang Loading…
5 tasks
2
[DNM][CI] Test H100 on CI
#221 opened Dec 5, 2025 by ywang96 Loading…
5 tasks
3
[Core] add clean up method for diffusion engine
#219 opened Dec 5, 2025 by ZJY0516 Loading…
5 tasks
8
Add Qwen3-omni offline UT
#216 opened Dec 5, 2025 by R2-Y Loading…
5 tasks
11
[Feature] Omni Connector + ray supported
#215 opened Dec 5, 2025 by natureofnature Loading…
5 tasks
15
[Profile] Adding profiling hooks for Qwen-Image diffusion pipeline
#214 opened Dec 5, 2025 by erfgss Loading…
1 task done
1
[Benchmark] Benchmark Running Samples for Qwen3 Omni and Dataset Preparation
#212 opened Dec 5, 2025 by tzhouam Loading…
3 of 5 tasks
6
[Model] [WIP] Add Flux2 Model support
#210 opened Dec 5, 2025 by LawJarp-A • Draft
2 of 5 tasks
1
[BugFix] Fix qwen3omni thinker batching.
#207 opened Dec 5, 2025 by yinpeiqi Loading…
5 tasks
3
[Bugfix] Support passing vllm cli args to online serving in vLLM-Omni bug Something isn't working
#206 opened Dec 5, 2025 by Gaohan123 Loading…
1 of 5 tasks
5
[Bugfix] Detach tensors in lists in the GPU/NPU model runners.
#205 opened Dec 5, 2025 by reubenvanammers Loading…
2
[Model] Add Wan2.2 text-to-video support new model add new model
#202 opened Dec 4, 2025 by linyueqian Loading…
5 tasks
@linyueqian
7
[Model] Add Qwen-Image-Edit new model add new model
#196 opened Dec 4, 2025 by SamitHuang Loading…
5 tasks
@SamitHuang
10
demo using docker for CI
#194 opened Dec 4, 2025 by khluu • Draft
1
[Feat] Support XPU Backend in vLLM-Omni
#191 opened Dec 4, 2025 by faaany • Draft
5 tasks
3
[Diffusion][WIP]: Diffusion Model Parallelism support
#189 opened Dec 4, 2025 by wtomin • Draft
5 tasks
Feature/teacache integration
#179 opened Dec 3, 2025 by LawJarp-A • Draft
3 of 5 tasks
17
[Misc] Initial Dockerfile
#170 opened Dec 3, 2025 by ywang96 Loading…
5 tasks
[CI] add cleanup_pr_body action
#156 opened Dec 2, 2025 by ZJY0516 • Draft
5 tasks
2
[Core] customize process between stages, remove the need of "request_ids" in model forward
#148 opened Dec 1, 2025 by yinpeiqi Loading…
5 tasks
3
[Doc] [ROCm]: Document the steps to run vLLM Omni on ROCm
#144 opened Dec 1, 2025 by tjtanaa • Draft
5 tasks
6
[Bugfix] Adjust Qwen3 Stage GPU utils
#140 opened Dec 1, 2025 by tzhouam Loading…
3 of 5 tasks
6
[Chore] Bump Python version and apply formatting changes for v0.12 release
#126 opened Dec 1, 2025 by DarkLight1337 • Draft
5 tasks
1
4
[CI] Run example file on Buildkite
#91 opened Nov 27, 2025 by ywang96 • Draft
5 tasks
ProTip! Add no:assignee to see everything that’s not assigned.