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

[MM][Model] Remove Qwen2-VL modeling files (#4534)

Browse Source 
### What this PR does / why we need it?

Following https://github.com/vllm-project/vllm-ascend/pull/4349, remove
Qwen2-VL modeling files.


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: shen-shanshan <467638484@qq.com>
This commit is contained in:
Shanshan Shen
2025-11-29 18:07:01 +08:00
committed by GitHub
parent 6664a4e5ce
commit 2a19215e5f
4 changed files with 212 additions and 590 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm_ascend/models/__init__.py
View File

@@ -2,10 +2,6 @@ from vllm import ModelRegistry
def register_model():
ModelRegistry.register_model(
"Qwen2VLForConditionalGeneration",
"vllm_ascend.models.qwen2_vl:AscendQwen2VLForConditionalGeneration")
ModelRegistry.register_model(
"Qwen3VLMoeForConditionalGeneration",
"vllm_ascend.models.qwen3_vl:AscendQwen3VLMoeForConditionalGeneration")