Feature Summary
Build with CUDA warning .CUDA V12.9
Detailed Description
[0/2] Re-checking globbed directories...
[1/191] Linking CXX static library ggml\src\ggml-base.lib
[2/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-dw.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-dw.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-dw.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-dw.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\conv2d-dw.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-dw.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[3/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\add-id.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\add-id.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\add-id.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\add-id.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\add-id.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[4/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-transpose.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-transpose.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-transpose.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-transpose.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\conv2d-transpose.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-transpose.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[5/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argmax.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argmax.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argmax.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argmax.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\argmax.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argmax.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[6/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cpy.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cpy.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cpy.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cpy.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\cpy.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cpy.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[7/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cumsum.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cumsum.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cumsum.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cumsum.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\cumsum.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cumsum.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[8/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\binbcast.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/binbcast.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\binbcast.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\binbcast.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\binbcast.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\binbcast.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[9/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\col2im-1d.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/col2im-1d.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\col2im-1d.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\col2im-1d.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\col2im-1d.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\col2im-1d.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[10/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\conv2d.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[11/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diag.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diag.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diag.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diag.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\diag.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diag.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[12/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cross-entropy-loss.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cross-entropy-loss.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cross-entropy-loss.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cross-entropy-loss.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\cross-entropy-loss.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cross-entropy-loss.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[13/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\acc.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\acc.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\acc.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\acc.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\acc.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[14/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\arange.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/arange.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\arange.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\arange.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\arange.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\arange.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[15/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\concat.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/concat.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\concat.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\concat.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\concat.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\concat.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[16/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\convert.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/convert.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\convert.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\convert.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\convert.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\convert.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[17/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argsort.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argsort.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argsort.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argsort.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\argsort.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argsort.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[18/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\allreduce.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/allreduce.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\allreduce.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\allreduce.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\allreduce.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\allreduce.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[19/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\count-equal.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/count-equal.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\count-equal.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\count-equal.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\count-equal.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\count-equal.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[20/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\clamp.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/clamp.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\clamp.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\clamp.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\clamp.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\clamp.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[21/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diagmask.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diagmask.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diagmask.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diagmask.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\diagmask.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diagmask.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[22/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv-transpose-1d.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv-transpose-1d.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv-transpose-1d.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv-transpose-1d.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\conv-transpose-1d.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv-transpose-1d.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[23/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\fattn-tile.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile.cu.obj
C:\PROGRA1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\fattn-tile.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\fattn-tile.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\fattn-tile.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\fattn-tile.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FS
C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
ninja: build stopped: subcommand failed.
Alternatives you considered
No response
Additional context
No response
Feature Summary
Build with CUDA warning .CUDA V12.9
Detailed Description
[0/2] Re-checking globbed directories...
[1/191] Linking CXX static library ggml\src\ggml-base.lib
[2/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-dw.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-dw.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-dw.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-dw.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\conv2d-dw.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-dw.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[3/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\add-id.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\add-id.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\add-id.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\add-id.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\add-id.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[4/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-transpose.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-transpose.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-transpose.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-transpose.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\conv2d-transpose.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d-transpose.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[5/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argmax.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argmax.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argmax.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argmax.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\argmax.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argmax.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[6/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cpy.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cpy.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cpy.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cpy.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\cpy.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cpy.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[7/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cumsum.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cumsum.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cumsum.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cumsum.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\cumsum.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cumsum.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[8/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\binbcast.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/binbcast.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\binbcast.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\binbcast.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\binbcast.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\binbcast.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[9/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\col2im-1d.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/col2im-1d.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\col2im-1d.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\col2im-1d.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\col2im-1d.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\col2im-1d.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[10/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\conv2d.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv2d.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[11/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diag.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diag.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diag.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diag.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\diag.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diag.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[12/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cross-entropy-loss.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cross-entropy-loss.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cross-entropy-loss.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cross-entropy-loss.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\cross-entropy-loss.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\cross-entropy-loss.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[13/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\acc.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\acc.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\acc.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\acc.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\acc.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[14/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\arange.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/arange.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\arange.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\arange.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\arange.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\arange.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[15/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\concat.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/concat.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\concat.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\concat.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\concat.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\concat.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[16/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\convert.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/convert.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\convert.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\convert.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\convert.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\convert.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[17/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argsort.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argsort.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argsort.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argsort.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\argsort.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\argsort.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[18/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\allreduce.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/allreduce.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\allreduce.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\allreduce.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\allreduce.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\allreduce.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[19/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\count-equal.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/count-equal.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\count-equal.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\count-equal.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\count-equal.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\count-equal.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[20/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\clamp.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/clamp.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\clamp.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\clamp.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\clamp.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\clamp.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[21/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diagmask.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diagmask.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diagmask.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diagmask.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\diagmask.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\diagmask.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[22/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv-transpose-1d.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv-transpose-1d.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv-transpose-1d.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv-transpose-1d.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\conv-transpose-1d.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\conv-transpose-1d.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
[23/191] Building CUDA object ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\fattn-tile.cu.obj
FAILED: ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile.cu.obj
C:\PROGRA
1\NVIDIA1\CUDA\v12.9\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_MAX_NAME=128 -DGGML_SCHED_MAX_COPIES=4 -DSD_BUILD_SHARED_LIB -D_CRT_SECURE_NO_WARNINGS -D_SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING -D_XOPEN_SOURCE=600 -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda.. -IC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\include" -D_WINDOWS -Xcompiler=" /GR /EHsc" -Xcompiler="-MDd -Zi -Ob0 -Od /RTC1" -std=c++17 "--generate-code=arch=compute_61,code=[sm_61]" /bigobj -use_fast_math -extended-lambda -compress-mode=size -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\fattn-tile.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\fattn-tile.cu.obj.d -x cu -c C:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\ggml\src\ggml-cuda\fattn-tile.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\fattn-tile.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\ggml-cuda.pdb,-FSC:\Users\杜涛\Downloads\stable-diffusion.cpp-master-773-1b04283\out\build\x64-Debug\EXEC : nvcc warning : Support for offline compilation for architectures prior to '<compute/sm/lto>_75' will be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified
ninja: build stopped: subcommand failed.
Alternatives you considered
No response
Additional context
No response