xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-01 22:57:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] Fix disabled v1 attention backend selection test (#25471)

Browse Source 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Isotr0py 2025-09-23 21:05:46 +08:00 committed by GitHub
parent 0d9fe260dd
commit b6a136b58c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/kernels/attention/test_attention_selector.py
View File

@ -67,7 +67,6 @@ def generate_params():
return params return params
@pytest.mark.skip(reason="Skipped for now. Should be revisited.")
@pytest.mark.parametrize("device, name, use_mla, block_size", @pytest.mark.parametrize("device, name, use_mla, block_size",
generate_params()) generate_params())
def test_env( def test_env(
@ -189,7 +188,7 @@ def test_env(
# FlashMLA only supports block_size == 64 # FlashMLA only supports block_size == 64
pytest.skip("FlashMLA only supports block_size 64") pytest.skip("FlashMLA only supports block_size 64")
else: else:
from vllm.attention.backends.flashmla import ( from vllm.v1.attention.backends.mla.flashmla import ( # noqa: E501
is_flashmla_supported) is_flashmla_supported)
is_supported, _ = is_flashmla_supported() is_supported, _ = is_flashmla_supported()
if not is_supported: if not is_supported: