tingfu f9842560cb [0.11.0][Perf] Add padding vision tower for Qwen2_5_Omni (#4041) ...

### What this PR does / why we need it?
This PR repalce the vision tower in Qwen2.5-Omni-Thinker model,
Qwen2_5_VisionTransformer, with AscendQwen2_5_VisionTransformer, which
use QKV padding for padding performance.

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

Signed-off-by: Ting FU <futing10@huawei.com>

2025-11-08 13:56:05 +08:00

..

layers

Revert "[Feat] Shared expert dp for deepseek and deepseek_mtp (#3495)" (#3586)

2025-10-21 22:24:30 +08:00

__init__.py

[0.11.0][Perf] Add padding vision tower for Qwen2_5_Omni (#4041)

2025-11-08 13:56:05 +08:00

deepseek_v3_2.py

[DeepSeek] Seperate deepseek v3.2 modeling form deepseek v2 (#3531)

2025-10-20 09:50:44 +08:00

qwen2_5_omni_thinker.py

[0.11.0][Perf] Add padding vision tower for Qwen2_5_Omni (#4041)

2025-11-08 13:56:05 +08:00

qwen2_5_vl_without_padding.py

Drop 0.10.2 (#3284)

2025-10-09 10:28:38 +08:00

qwen2_5_vl.py

[0.11.0][Perf] Add padding vision tower for Qwen2_5_Omni (#4041)

2025-11-08 13:56:05 +08:00

qwen2_vl.py

fix vl float model not support NZ format weight error (#3533)

2025-10-21 22:23:17 +08:00

qwen3_next.py

[BugFix] Fix Qwen3-Next because of vllm #24982 (#3221)

2025-09-29 15:27:30 +08:00