xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-25 09:16:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix broken test vllm:test_kernels - test_attention_selector.py::test_flash_attn (#17873)

Browse Source 
Co-authored-by: Stephen Chen <tracelog@meta.com>
This commit is contained in:
tracelogfb 2025-05-09 19:46:54 -07:00 committed by GitHub
parent 7042cc96b0
commit 246e3e0a36
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tests/kernels/attention/test_attention_selector.py
View File

@ -188,8 +188,9 @@ def test_flash_attn(monkeypatch: pytest.MonkeyPatch):
m.setenv(STR_BACKEND_ENV_VAR, STR_FLASH_ATTN_VAL)
# Unsupported CUDA arch
monkeypatch.setattr(torch.cuda, "get_device_capability", lambda:
(7, 5))
monkeypatch.setattr(torch.cuda,
"get_device_capability",
lambda _=None: (7, 5))
backend = get_attn_backend(16, torch.float16, None, 16, False)
assert backend.get_name() != STR_FLASH_ATTN_VAL