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

[Feat][Graph] Support DeepSeek with ACL Graph (#2707)

Browse Source 
### What this PR does / why we need it?
In memory of #677 , a long overdue milestone. Now DeepSeek V3/R1 should
be OK with ACL Graph.

### Does this PR introduce _any_ user-facing change?
None.

### How was this patch tested?
Working on it.

- vLLM version: v0.10.2
- vLLM main:
68dbde5dbb

---------

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
This commit is contained in:
yiz-liu
2025-09-16 17:50:17 +08:00
committed by GitHub
parent 3e60aa5483
commit 88ca8a051c
7 changed files with 64 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/models/deepseek_v2.py
View File

@@ -50,7 +50,7 @@ from vllm.model_executor.model_loader.weight_utils import (
default_weight_loader, maybe_remap_kv_scale_name)
from vllm.model_executor.models.deepseek_v2 import \
yarn_get_mscale # noqa: E501
from vllm.model_executor.models.deepseek_v2 import ( # noqa: E501
from vllm.model_executor.models.deepseek_v2 import (
DeepseekV2Attention, DeepseekV2DecoderLayer, DeepseekV2ForCausalLM,
DeepseekV2MLAAttention, DeepseekV2MLP, DeepseekV2Model, DeepseekV2MoE,
get_spec_layer_idx_from_weight_name)