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 9, 23:00 UTC
[Bugfix] Suppress log on non-ROCm platform (#32703)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
TJian committed
Jan 21, 2026 at 05:38 UTC
9b67338b78f33dca5726191cead98ed913a96f4a
1 file changed
+5
-4
vllm/model_executor/layers/quantization/quark/schemes/quark_ocp_mx.py
+5
-4
@@ -154,10 +154,11 @@ try:
154
dispatch_key=current_platform.dispatch_key,
155
)
156
except (ImportError, AttributeError, RuntimeError):
157
- logger.warning(
158
- "AITER is not found or QuarkOCP_MX is not supported on the current "
159
- "platform. QuarkOCP_MX quantization will not be available."
160
- )
157
+ if current_platform.is_rocm():
158
+ logger.warning(
159
+ "AITER is not found or QuarkOCP_MX is not supported on the current "
160
+ "platform. QuarkOCP_MX quantization will not be available."
161
+ )
162
dynamic_mxfp4_quant = gemm_afp4wfp4 = None
163
164