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 14, 05:30 UTC
[Bugfix] Fix import `gemm_afp4wfp4` failure on AMD (#26068)
Signed-off-by: zhewenli <zhewenli@meta.com>
Zhewen Li committed
Oct 2, 2025 at 22:37 UTC
711f485643af9e6e9622d43caa8b020b6026bc15
1 file changed
+1
-1
vllm/model_executor/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py
+1
-1
@@ -97,7 +97,7 @@ try:
97
dispatch_key=current_platform.dispatch_key,
98
)
99
100
-except ImportError:
100
+except (ImportError, AttributeError):
101
dynamic_mxfp4_quant = gemm_afp4wfp4 = None
102
103
__all__ = ["QuarkW4A4MXFP4"]