biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Convert formatting to use ruff instead of yapf + isort (#26247)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-05 15:06:22 +01:00
committed by GitHub
parent 17edd8a807
commit d6953beb91
1508 changed files with 115244 additions and 94146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
tests/v1/spec_decode/test_max_len.py
View File

@@ -33,17 +33,19 @@ def test_ngram_max_len(num_speculative_tokens: int):
@pytest.mark.parametrize("num_speculative_tokens", [1, 3, 10])
@pytest.mark.parametrize("attn_backend",
get_attn_backend_list_based_on_platform())
def test_eagle_max_len(monkeypatch: pytest.MonkeyPatch,
num_speculative_tokens: int, attn_backend: str):
@pytest.mark.parametrize("attn_backend", get_attn_backend_list_based_on_platform())
def test_eagle_max_len(
monkeypatch: pytest.MonkeyPatch, num_speculative_tokens: int, attn_backend: str
):
with monkeypatch.context() as m:
m.setenv("VLLM_USE_V1", "1")
m.setenv("VLLM_ATTENTION_BACKEND", attn_backend)
if (attn_backend == "TRITON_ATTN" and not current_platform.is_rocm()):
pytest.skip("TRITON_ATTN does not support "
"multi-token eagle spec decode on current platform")
if attn_backend == "TRITON_ATTN" and not current_platform.is_rocm():
pytest.skip(
"TRITON_ATTN does not support "
"multi-token eagle spec decode on current platform"
)
if attn_backend == "FLASH_ATTN" and current_platform.is_rocm():
m.setenv("VLLM_ROCM_USE_AITER", "1")