@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 84eaa68425
Fork 0

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 17, 04:15 UTC

Abort when nvcc command is not found in the PATH (#3527)

Allen.Dou committed Mar 21, 2024 at 00:28 UTC 84eaa68425807a490f363d2e5ddf9bee3d362b0d
1 file changed +6
CMakeLists.txt
+6
@@ -49,6 +49,12 @@ endif()
49 #
50 append_cmake_prefix_path("torch" "torch.utils.cmake_prefix_path")
51
52 +# Ensure the 'nvcc' command is in the PATH
53 +find_program(NVCC_EXECUTABLE nvcc)
54 +if (NOT NVCC_EXECUTABLE)
55 + message(FATAL_ERROR "nvcc not found")
56 +endif()
57 +
58 #
59 # Import torch cmake configuration.
60 # Torch also imports CUDA (and partially HIP) languages with some customizations,