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

[Model][1/N] Delete deepseek v2/v3 modeling codes. (#3189)

Browse Source 
This PR deletes model codes of deepseek_v2 and deepseek_v3 to reuse the
model file from vLLM.

vLLM Ascend now uses custom ops register way instead of model file
hard-coding.

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: whx-sjtu <2952154980@qq.com>
This commit is contained in:
whx
2025-10-20 15:31:34 +08:00
committed by GitHub
parent 918ded9155
commit f8b52fe950
13 changed files with 143 additions and 843 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/ut/models/test_deepseek_mtp.py
View File

@@ -37,8 +37,6 @@ class TestCustomDeepSeekMultiTokenPredictorLayer(PytestBase):
mocker.patch(
"vllm_ascend.ops.vocab_parallel_embedding.AscendVocabParallelEmbedding.__init__",
return_value=None)
mocker.patch("vllm_ascend.models.deepseek_v2.get_ascend_config",
return_value=mocker.Mock())
mtp_layer = CustomDeepSeekMultiTokenPredictorLayer(config, "0", None)
mocker_deepseek_v2_decode_layer.assert_called_once()