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

[ROCm][CI] Fix test_max_len.py for Rocm (#29916)

Browse Source 
Signed-off-by: charlifu <charlifu@amd.com>
Signed-off-by: Charlie Fu <Charlie.Fu@amd.com>
This commit is contained in:
Charlie Fu
2025-12-08 15:58:30 -06:00
committed by GitHub
parent ae0f69b16a
commit 6af70e11a0
5 changed files with 15 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/v1/e2e/test_spec_decode.py
View File

@@ -417,9 +417,9 @@ def test_eagle_correctness(
"multi-token eagle spec decode on current platform"
)
if attn_backend == "FLASH_ATTN" and current_platform.is_rocm():
if attn_backend == "ROCM_AITER_FA" and current_platform.is_rocm():
if "deepseek" in model_setup[1].lower():
pytest.skip("FLASH_ATTN for deepseek not supported on ROCm platform")
pytest.skip("ROCM_AITER_FA for deepseek not supported on ROCm platform")
else:
m.setenv("VLLM_ROCM_USE_AITER", "1")