A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 11, 15:00 UTC
[CI/Build][AMD] Skip test_cutlass_w4a8_moe tests on ROCm sine they require cutlass_pack_scale_fp8 (#30508)
Signed-off-by: Randall Smith <ransmith@amd.com> Signed-off-by: Michael Goin <mgoin64@gmail.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Randall Smith <ransmith@amd.com> Co-authored-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
rasmith committed
Dec 11, 2025 at 19:02 UTC
ba809266818cfb9e63bcb34d79fdd77af6e308fe
1 file changed
+3
-1
tests/kernels/quantization/test_cutlass_w4a8_moe.py
+3
-1
@@ -18,7 +18,9 @@ from vllm.model_executor.layers.quantization.utils.quant_utils import (
18
from vllm.platforms import current_platform
19
from vllm.scalar_type import ScalarType, scalar_types
20
21
-IS_SUPPORTED_BY_GPU = current_platform.get_device_capability()[0] >= 9
21
+IS_SUPPORTED_BY_GPU = (
22
+ current_platform.is_cuda() and current_platform.get_device_capability()[0] >= 9
23
+)
24
25
26
def to_fp8(tensor: torch.Tensor) -> torch.Tensor: