Skip to content

Qwen3vl qwen3omni #1982

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Draft
wants to merge 9 commits into
base: aice/v1.22.0
Choose a base branch
from
Draft

Qwen3vl qwen3omni #1982

wants to merge 9 commits into from

Conversation

wenbinc-Bin
Copy link

@wenbinc-Bin wenbinc-Bin commented Sep 25, 2025 •
edited by github-actions bot
Loading

Purpose

Porting qwen3-vl and qwen3-omni to vllm-fork

Test Plan

PT_HPU_LAZY_MODE=1 VLLM_SKIP_WARMUP=true python examples/offline_inference/vision_language.py --modality image --model-type qwen3_vl_moe
PT_HPU_LAZY_MODE=1 VLLM_SKIP_WARMUP=true python examples/offline_inference/vision_language.py --modality video --model-type qwen3_vl_moe
PT_HPU_LAZY_MODE=1 VLLM_SKIP_WARMUP=true python examples/offline_inference/vision_language.py --modality image --model-type qwen3_omni_moe
PT_HPU_LAZY_MODE=1 VLLM_SKIP_WARMUP=true python examples/offline_inference/vision_language.py --modality video --model-type qwen3_omni_moe

ywang96 and others added 7 commits September 25, 2025 09:20
@ywang96 @JJJYmmm
@wulipc @Isotr0py @wenbinc-Bin
Support Qwen3-VL Model Series (vllm-project#24727)
d23b757 
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Isotr0py <[email protected]>
Co-authored-by: Huang Jie <[email protected]>
Co-authored-by: 松灵 <[email protected]>
Co-authored-by: Isotr0py <[email protected]>
@wenbinc-Bin
enable qwen3-vl on gaudi
3778291 
Signed-off-by: Chen, Wenbin <[email protected]>
@wenbinc-Bin
enable qwen3-vl on vision_language.py
812831e 
Signed-off-by: Chen, Wenbin <[email protected]>
@wenbinc-Bin
Add Qwen3-Omni moe thinker (vllm-project#25550)
df7c572 
vllm-project#25550

Signed-off-by: Chen, Wenbin <[email protected]>
@wenbinc-Bin
enable qwen3-omni on gaudi
77b3753 
Signed-off-by: Chen, Wenbin <[email protected]>
@wenbinc-Bin
Enable qwen3-omni in vision_launage.py
72bf664 
Signed-off-by: Chen, Wenbin <[email protected]>
@wenbinc-Bin
Add qwen3-vl qwen3-omni placeholders
03f479b 
Signed-off-by: Chen, Wenbin <[email protected]>
@wenbinc-Bin wenbinc-Bin marked this pull request as draft September 25, 2025 09:23
@wenbinc-Bin
Fix Qwen3-VL precession bug
4957c40 
Avoid using instance variable when using hpu_graph.

Signed-off-by: Chen, Wenbin <[email protected]>
@wenbinc-Bin
Fix qwen3-omni precession bug
53d9351 
Avoid using instance variable when using hpu_graph.

Signed-off-by: Chen, Wenbin <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@kzawora-intel kzawora-intel Awaiting requested review from kzawora-intel kzawora-intel is a code owner

@madamczyk-intel madamczyk-intel Awaiting requested review from madamczyk-intel madamczyk-intel is a code owner

@michalkuligowski michalkuligowski Awaiting requested review from michalkuligowski michalkuligowski is a code owner

@mgawarkiewicz-intel mgawarkiewicz-intel Awaiting requested review from mgawarkiewicz-intel mgawarkiewicz-intel is a code owner

@vivekgoe vivekgoe Awaiting requested review from vivekgoe vivekgoe is a code owner

@afierka-intel afierka-intel Awaiting requested review from afierka-intel afierka-intel is a code owner

@xuechendi xuechendi Awaiting requested review from xuechendi xuechendi is a code owner

@jikunshang jikunshang Awaiting requested review from jikunshang jikunshang is a code owner

@mswiniarsk mswiniarsk Awaiting requested review from mswiniarsk mswiniarsk is a code owner

@PatrykWo PatrykWo Awaiting requested review from PatrykWo PatrykWo is a code owner

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@wenbinc-Bin @ywang96