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

Drop vLLM 0.13.0 support (#6069)

Browse Source 
### What this PR does / why we need it?
Drop vLLM 0.13.0 support, upgrade to 0.14.0

- vLLM version: v0.13.0
- vLLM main:
d68209402d

---------

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
zhangxinyuehfad
2026-01-23 09:45:08 +08:00
committed by GitHub
parent 27a513b672
commit 819a4459ce
39 changed files with 86 additions and 272 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/ut/attention/test_mla_v1.py
View File

@@ -17,7 +17,6 @@ from vllm_ascend.attention.mla_v1 import (AscendMLABackend,
AscendMLAPrefillMetadata,
ChunkedContextMetadata)
from vllm_ascend.attention.utils import AscendCommonAttentionMetadata
from vllm_ascend.utils import vllm_version_is
class TestAscendMLABackend(TestBase):
@@ -477,10 +476,7 @@ class TestAscendMLAMetadataBuilderBuild(TestBase):
self.mock_vllm_config.model_config = model_config
self.kv_cache_spec = MagicMock()
self.kv_cache_spec.num_layers = 32
if vllm_version_is('0.13.0'):
self.kv_cache_spec.head_size = 128
else:
self.kv_cache_spec.head_size = 64
self.kv_cache_spec.head_size = 64
self.kv_cache_spec.num_heads = 32
def tearDown(self):