xc-llm-ascend

Files

Levi 3b4cb23616 [Bugfix] fix qwen2.5-vl-72b shape ERROR during the _prepare_inputs phase under high concurrency. (#4553 )

### What this PR does / why we need it?
qwen2.5-vl-72b reports a shape ERROR during the _prepare_inputs phase
under high concurrency【 issue
https://github.com/vllm-project/vllm-ascend/issues/4430 】

This PR fix it.

The related PR in main branch
:https://github.com/vllm-project/vllm-ascend/pull/3612

The related commit in vllm :
17c540a993/vllm/model_executor/models/interfaces.py

【The _get_text_embeddings function has been refactored to
interfaces.pyin vllm.】

Signed-off-by: Levi-JQ <yujinqi2@huawei.com>
Co-authored-by: Levi-JQ <yujinqi2@huawei.com>

2025-12-02 14:20:45 +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 )