EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[CherryPick] Add unpadded Qwen2.5-VL for verl scenario (#1095)

Browse Source 
Add unpadded Qwen2.5-VL for verl scenario.

When using vllm-ascend for verl scenario, set `USE_OPTIMIZED_QWEN2_5_VL`
(default `1`) to `0` to use unpadded Qwen2.5-VL to avoid errors.

This is cherry-picked from 0.7.3-dev

Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
This commit is contained in:
wangxiyuan
2025-06-07 19:45:46 +08:00
committed by GitHub
parent b80a484864
commit c8742146d3
3 changed files with 288 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
vllm_ascend/models/__init__.py
View File

@@ -20,10 +20,16 @@ def register_model():
"Qwen2VLForConditionalGeneration",
"vllm_ascend.models.qwen2_vl:AscendQwen2VLForConditionalGeneration")
ModelRegistry.register_model(
"Qwen2_5_VLForConditionalGeneration",
"vllm_ascend.models.qwen2_5_vl:AscendQwen2_5_VLForConditionalGeneration"
)
if envs.USE_OPTIMIZED_MODEL:
ModelRegistry.register_model(
"Qwen2_5_VLForConditionalGeneration",
"vllm_ascend.models.qwen2_5_vl:AscendQwen2_5_VLForConditionalGeneration"
)
else:
ModelRegistry.register_model(
"Qwen2_5_VLForConditionalGeneration",
"vllm_ascend.models.qwen2_5_vl_without_padding:AscendQwen2_5_VLForConditionalGeneration_Without_Padding"
)
if envs.VLLM_ASCEND_ENABLE_DBO:
ModelRegistry.register_model(