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

[CI/Build][AMD] Fix import errors in tests/kernels/attention (#29032)

Browse Source 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
This commit is contained in:
rasmith
2025-11-20 03:48:09 -06:00
committed by GitHub
parent 2c52c7fd9a
commit 322cb02872
6 changed files with 49 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/kernels/moe/test_flashinfer.py
View File

@@ -22,7 +22,14 @@ from vllm.model_executor.layers.quantization.utils.flashinfer_utils import (
from vllm.model_executor.layers.quantization.utils.fp8_utils import input_to_float8
from vllm.model_executor.models.llama4 import Llama4MoE
from vllm.platforms import current_platform
from vllm.utils.flashinfer import has_flashinfer_cutlass_fused_moe
try:
from vllm.utils.flashinfer import has_flashinfer_cutlass_fused_moe
except ImportError:
if current_platform.is_rocm():
pytest.skip(
"flashinfer not supported for vLLM on ROCm", allow_module_level=True
)
if not has_flashinfer_cutlass_fused_moe() or not current_platform.has_device_capability(
90