Li Wang 968e6791d3 [Misc] Add data preprocess functions to qwen2.5_vl_without_padding (#2148) ...

### What this PR does / why we need it?
Cherry pick #1705 from v0.9.1-dev
Compared qwen2_5_vl.py, qwen2_5_vl_without_padding.py missing some
funtions. The purpose of this PR is to supplement these.

add:
- rot_pos_emb(self, grid_thw: torch.Tensor)
- get_window_index(self, grid_thw)
- _process_image_input(self, image_input)
- _process_video_input(self, video_input)

Co-authored-by: zheliuyu
[15750543867@163.com](mailto:15750543867@163.com)
Co-authored-by: wangli
[wangli858794774@gmail.com](mailto:wangli858794774@gmail.com)

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.10.0
- vLLM main:
207b750e19

Signed-off-by: wangli <wangli858794774@gmail.com>

2025-08-01 08:54:02 +08:00

..

__init__.py

[main] Use AddRmsNormQuant ops in the custom model to optimize Qwen3's performance (#1806)

2025-07-22 19:03:13 +08:00

deepseek_dbo.py

[main][refactor] Refactoring forward_context and model_runner_v1 (#1979)

2025-07-28 14:06:20 +08:00

deepseek_mtp.py

[Feature] Enable inference support for Deepseekr1-w8a8-MTP (#1994)

2025-07-29 18:51:57 +08:00

deepseek_v2.py

[Perf][MoE] Improve MoE multistream parallel performace. (#1891)

2025-07-29 23:53:19 +08:00

deepseek_v3.py

Move deepseek_v3 from deepseek_v2.py (#1793)

2025-07-19 11:37:03 +08:00

pangu_moe.py

[Misc] Fix logger bug (#2024)

2025-07-28 15:59:09 +08:00

qwen2_5_vl_without_padding.py

[Misc] Add data preprocess functions to qwen2.5_vl_without_padding (#2148)

2025-08-01 08:54:02 +08:00

qwen2_5_vl.py

[Bug] Fix duplicate 'torch.' prefix in qwen-vl (#1986)

2025-07-24 20:16:00 +08:00

qwen2_vl.py

[Bug] Fix duplicate 'torch.' prefix in qwen-vl (#1986)

2025-07-24 20:16:00 +08:00

qwen3_moe.py

[Feature] Add CustomQwen3MoeForCausalLM model (#925)

2025-05-23 15:50:48 +08:00

qwen3.py

[main] Use AddRmsNormQuant ops in the custom model to optimize Qwen3's performance (#1806)

2025-07-22 19:03:13 +08:00