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

[Model][3/N] Refactor sfa into mla and remove deepseek_v3_2.py (#3769)

Browse Source 
This is the follow-up PR to PR #3189, which continues to refactor sfa
into mla and finally remove deepseek_v3_2.py. This is the last PR of
deepseek modeling refactoring. After this, all deepseek-related model
codes are removed from vllm_ascend.

FurtherMore, after this PR deepseek v3.2 can run chunk-prefill with
correct accuracy.

- vLLM version: v0.11.0rc3
- vLLM main:
83f478bb19

---------

Signed-off-by: whx-sjtu <2952154980@qq.com>
This commit is contained in:
whx
2025-10-30 17:06:38 +08:00
committed by GitHub
parent eff3e5fc6f
commit f6149f3894
10 changed files with 751 additions and 1935 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm_ascend/patch/worker/__init__.py
View File

@@ -33,3 +33,4 @@ from vllm_ascend.utils import vllm_version_is
if vllm_version_is("0.11.0"):
import vllm_ascend.patch.worker.patch_deepseek_mtp # noqa
import vllm_ascend.patch.worker.patch_deepseek_v3_2 # noqa