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

Move deepseek_v3 from deepseek_v2.py (#1793)

Browse Source 
### What this PR does / why we need it?
Before patch, we can see
`vllm_ascend.models.deepseek_v2:CustomDeepseekV3ForCausalLM`, it seems
not friendly format.

```
WARNING 07-14 23:57:34 [registry.py:413] Model architecture DeepseekV2ForCausalLM is already registered, and will be overwritten by the new model class vllm_ascend.models.deepseek_v2:CustomDeepseekV2ForCausalLM.
WARNING 07-14 23:57:34 [registry.py:413] Model architecture DeepseekV3ForCausalLM is already registered, and will be overwritten by the new model class vllm_ascend.models.deepseek_v2:CustomDeepseekV3ForCausalLM.
WARNING 07-14 23:57:34 [registry.py:413] Model architecture Qwen3MoeForCausalLM is already registered, and will be overwritten by the new model class vllm_ascend.models.qwen3_moe:CustomQwen3MoeForCausalLM.
```


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

No.

### How was this patch tested?

Local Test.


- vLLM version: v0.9.2
- vLLM main:
bcdfb2a330

Signed-off-by: xleoken <xleoken@163.com>
This commit is contained in:
xleoken
2025-07-19 11:37:03 +08:00
committed by GitHub
parent ab68d31a24
commit b824525be3
3 changed files with 29 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm_ascend/models/deepseek_v2.py
View File

@@ -979,7 +979,3 @@ class CustomDeepseekV2ForCausalLM(DeepseekV2ForCausalLM):
attn_metadata, intermediate_tensors,
inputs_embeds)
return hidden_states
class CustomDeepseekV3ForCausalLM(CustomDeepseekV2ForCausalLM):
pass