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

[Misc] Code clean up (#1679)

Browse Source 
Make model_runner_v1 more readable

- vLLM version: v0.9.2
- vLLM main:
baed180aa0

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-07-09 14:33:40 +08:00
committed by GitHub
parent 392fd7239b
commit b979ee353d
2 changed files with 138 additions and 254 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/worker/eagle_proposer_v1.py
View File

@@ -14,7 +14,7 @@ from vllm.model_executor.models import supports_multimodal
from vllm.model_executor.models.llama_eagle3 import Eagle3LlamaForCausalLM
from vllm.v1.sample.metadata import SamplingMetadata
from vllm_ascend.attention.attention import AttentionMaskBuilder
from vllm_ascend.attention.attention_mask import AttentionMaskBuilder
from vllm_ascend.attention.attention_v1 import AscendAttentionState
logger = init_logger(__name__)