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

clean 0.15.0 support (#6852)

Browse Source 
Clean up vllm 0.15.0 related code

- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2026-02-28 09:20:57 +08:00
committed by GitHub
parent 84b00695f8
commit 3d563292f3
8 changed files with 17 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/ut/attention/test_sfa_v1.py
View File

@@ -14,7 +14,7 @@ if 'torch_npu._inductor' not in sys.modules:
from vllm_ascend.attention.sfa_v1 import (AscendSFABackend, AscendSFAImpl,
AscendSFAMetadata,
AscendSFAMetadataBuilder)
from vllm_ascend.utils import enable_dsa_cp, vllm_version_is
from vllm_ascend.utils import enable_dsa_cp
class TestAscendSFABackend(TestBase):

2
tests/ut/quantization/test_modelslim_config.py
View File

@@ -13,7 +13,7 @@ from vllm_ascend.quantization.modelslim_config import (
MODELSLIM_CONFIG_FILENAME,
AscendModelSlimConfig,
)
from vllm_ascend.utils import ASCEND_QUANTIZATION_METHOD, vllm_version_is
from vllm_ascend.utils import ASCEND_QUANTIZATION_METHOD
from vllm.model_executor.layers.attention import Attention