diff --git a/extensions/inference-cortex-extension/download.bat b/extensions/inference-cortex-extension/download.bat index e19786971..6d917cf79 100644 --- a/extensions/inference-cortex-extension/download.bat +++ b/extensions/inference-cortex-extension/download.bat @@ -18,8 +18,8 @@ call .\node_modules\.bin\download %DOWNLOAD_URL%-avx.tar.gz -e --strip 1 -o %BIN call .\node_modules\.bin\download %DOWNLOAD_URL%-avx2.tar.gz -e --strip 1 -o %BIN_PATH%/avx2/engines/cortex.llamacpp call .\node_modules\.bin\download %DOWNLOAD_URL%-avx512.tar.gz -e --strip 1 -o %BIN_PATH%/avx512/engines/cortex.llamacpp call .\node_modules\.bin\download %DOWNLOAD_URL%-vulkan.tar.gz -e --strip 1 -o %BIN_PATH%/vulkan/engines/cortex.llamacpp -call .\node_modules\.bin\download %CUDA_DOWNLOAD_URL%-cuda-12-0-windows-amd64.tar.gz -e --strip 1 -o %BIN_PATH% -call .\node_modules\.bin\download %CUDA_DOWNLOAD_URL%-cuda-11-7-windows-amd64.tar.gz -e --strip 1 -o %BIN_PATH% +call .\node_modules\.bin\download %CUDA_DOWNLOAD_URL%/cuda-12-0-windows-amd64.tar.gz -e --strip 1 -o %BIN_PATH% +call .\node_modules\.bin\download %CUDA_DOWNLOAD_URL%/cuda-11-7-windows-amd64.tar.gz -e --strip 1 -o %BIN_PATH% @REM Loop through each folder and move DLLs (excluding engine.dll) diff --git a/extensions/inference-cortex-extension/download.sh b/extensions/inference-cortex-extension/download.sh index 9426bc872..3e809765c 100755 --- a/extensions/inference-cortex-extension/download.sh +++ b/extensions/inference-cortex-extension/download.sh @@ -23,8 +23,8 @@ if [ "$OS_TYPE" == "Linux" ]; then download "${ENGINE_DOWNLOAD_URL}-linux-amd64-noavx-cuda-12-0.tar.gz" -e --strip 1 -o "./bin/noavx-cuda-12-0/engines/cortex.llamacpp" 1 download "${ENGINE_DOWNLOAD_URL}-linux-amd64-noavx-cuda-11-7.tar.gz" -e --strip 1 -o "./bin/noavx-cuda-11-7/engines/cortex.llamacpp" 1 download "${ENGINE_DOWNLOAD_URL}-linux-amd64-vulkan.tar.gz" -e --strip 1 -o "./bin/vulkan/engines/cortex.llamacpp" 1 - download "${CUDA_DOWNLOAD_URL}-cuda-12-0-linux-amd64.tar.gz" -e --strip 1 -o "./bin" 1 - download "${CUDA_DOWNLOAD_URL}-cuda-11-7-linux-amd64.tar.gz" -e --strip 1 -o "./bin" 1 + download "${CUDA_DOWNLOAD_URL}/cuda-12-0-linux-amd64.tar.gz" -e --strip 1 -o "./bin" 1 + download "${CUDA_DOWNLOAD_URL}/cuda-11-7-linux-amd64.tar.gz" -e --strip 1 -o "./bin" 1 elif [ "$OS_TYPE" == "Darwin" ]; then # macOS downloads diff --git a/extensions/inference-cortex-extension/src/node/execute.ts b/extensions/inference-cortex-extension/src/node/execute.ts index b8e768bb9..74ffb48c6 100644 --- a/extensions/inference-cortex-extension/src/node/execute.ts +++ b/extensions/inference-cortex-extension/src/node/execute.ts @@ -91,15 +91,15 @@ export const executableCortexFile = ( : process.platform === 'darwin' ? os() : [ - gpuRunMode(gpuSetting) !== 'cuda' || - cpuInstruction === 'avx2' - ? cpuInstruction - : 'noavx', - gpuRunMode(gpuSetting), - cudaVersion(gpuSetting), - ] - .filter((e) => !!e) - .join('-') + gpuRunMode(gpuSetting) !== 'cuda' || + cpuInstruction === 'avx2' || cpuInstruction === 'avx512' + ? cpuInstruction + : 'noavx', + gpuRunMode(gpuSetting), + cudaVersion(gpuSetting), + ] + .filter((e) => !!e) + .join('-') let cudaVisibleDevices = gpuSetting?.gpus_in_use.join(',') ?? '' let vkVisibleDevices = gpuSetting?.gpus_in_use.join(',') ?? '' let binaryName = `cortex-server${extension()}`