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 15, 04:45 UTC
[Misc][ROCm] Enforce no unused variable in ROCm C++ files (#19796)
Signed-off-by: Lu Fang <lufang@fb.com>
Lu Fang committed
Jun 19, 2025 at 11:25 UTC
8d1e89d946e8f72580233b4541834110b62a257b
1 file changed
+1
cmake/utils.cmake
+1
@@ -122,6 +122,7 @@ function (get_torch_gpu_compiler_flags OUT_GPU_FLAGS GPU_LANG)
122
"-DENABLE_FP8"
123
"-U__HIP_NO_HALF_CONVERSIONS__"
124
"-U__HIP_NO_HALF_OPERATORS__"
125
+ "-Werror=unused-variable"
126
"-fno-gpu-rdc")
127
128
endif()