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

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

View File

@@ -656,7 +656,8 @@ class AscendMLATorchairImpl(MLAAttentionImpl):
self.qk_head_dim = kwargs['qk_head_dim']
self.v_head_dim = kwargs['v_head_dim']
self.rotary_emb = kwargs['rotary_emb']
self.q_proj = kwargs['q_proj']
self.q_proj = kwargs['q_proj'] if self.q_lora_rank is None else kwargs[
'q_b_proj']
self.kv_b_proj = kwargs['kv_b_proj']
self.o_proj = kwargs['o_proj']
self.kv_a_proj_with_mqa = kwargs.get('kv_a_proj_with_mqa', None)