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

[Test] Remove VLLM_USE_V1 in example and tests (#1733)

Browse Source 
V1 is enabled by default, no need to set it by hand now. This PR remove
the useless setting in example and tests

- vLLM version: v0.9.2
- vLLM main:
9ad0a4588b

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-07-15 12:49:57 +08:00
committed by GitHub
parent eb921d2b6f
commit 787010a637
29 changed files with 186 additions and 291 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/e2e/multicard/test_offline_inference_distributed.py
View File

@@ -27,7 +27,7 @@ from modelscope import snapshot_download # type: ignore
from vllm import SamplingParams
from vllm.model_executor.models.registry import ModelRegistry
from tests.conftest import VllmRunner
from tests.e2e.conftest import VllmRunner
os.environ["PYTORCH_NPU_ALLOC_CONF"] = "max_split_size_mb:256"