Is Kepler GPU (Tesla K80) not supported?
xiasi0 opened this issue · 2 comments
K80 is a very old GPU, is it supported in whipper.cpp? This is my NVIDIA driver version, CUDA version, and GCC/G++version
NVIDIA driver version：471.11
CUDA version：11.4.0
gcc version：13.2.0
g++ version：13.2.0
The system is Windows
I think you need at least CUDA 11.7
我认为您至少需要 CUDA 11.7
Thank you for your reply. I upgraded cuda11.7, but received the following error message while making:
Firstly, it reminds me that devices with 3.7 computing power may not support it in the future. Secondly, it prompts me that many files cannot be found, and an error message is reported below. Are these error messages saying that the GPU does not support this architecture? I don't quite understand
I whisper.cpp build info:
I UNAME_S: MINGW64_NT-10.0-20348
I UNAME_P: unknown
I UNAME_M: x86_64
I CFLAGS: -I. -O3 -DNDEBUG -std=c11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include
I LDFLAGS: -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -LC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/lib -L/usr/lib/wsl/lib
I CC: cc.exe (x86_64-win32-seh-rev1, Built by MinGW-Builds project) 13.2.0
I CXX: c++.exe (x86_64-win32-seh-rev1, Built by MinGW-Builds project) 13.2.0
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -Wno-pedantic -c ggml-cuda.cu -o ggml-cuda.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/acc.cu -o ggml-cuda/acc.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/alibi.cu -o ggml-cuda/alibi.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/arange.cu -o ggml-cuda/arange.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/argsort.cu -o ggml-cuda/argsort.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/binbcast.cu -o ggml-cuda/binbcast.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/clamp.cu -o ggml-cuda/clamp.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/concat.cu -o ggml-cuda/concat.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/convert.cu -o ggml-cuda/convert.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/cpy.cu -o ggml-cuda/cpy.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/diagmask.cu -o ggml-cuda/diagmask.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/dmmv.cu -o ggml-cuda/dmmv.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/getrows.cu -o ggml-cuda/getrows.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/im2col.cu -o ggml-cuda/im2col.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/mmq.cu -o ggml-cuda/mmq.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/mmvq.cu -o ggml-cuda/mmvq.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/norm.cu -o ggml-cuda/norm.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/pad.cu -o ggml-cuda/pad.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/pool2d.cu -o ggml-cuda/pool2d.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/quantize.cu -o ggml-cuda/quantize.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/rope.cu -o ggml-cuda/rope.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/scale.cu -o ggml-cuda/scale.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/softmax.cu -o ggml-cuda/softmax.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/sumrows.cu -o ggml-cuda/sumrows.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/tsembd.cu -o ggml-cuda/tsembd.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/unary.cu -o ggml-cuda/unary.o
nvcc --forward-unknown-to-host-compiler -arch=native -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-cuda/upscale.cu -o ggml-cuda/upscale.o
cc -I. -O3 -DNDEBUG -std=c11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml.c -o ggml.o
cc -I. -O3 -DNDEBUG -std=c11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-alloc.c -o ggml-alloc.o
cc -I. -O3 -DNDEBUG -std=c11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-backend.c -o ggml-backend.o
cc -I. -O3 -DNDEBUG -std=c11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c ggml-quants.c -o ggml-quants.o
c++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -D_XOPEN_SOURCE=600 -msse3 -mssse3 -mavx -DGGML_USE_CUDA -I/usr/local/cuda/include -I/opt/cuda/include -IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7/targets/x86_64-linux/include -c whisper.cpp -o whisper.o
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/cpy.o] Error 1
make: *** Waiting for unfinished jobs....
make: *** [Makefile:299: ggml-cuda.o] Error 1
make: *** [Makefile:296: ggml-cuda/alibi.o] Error 1
make: *** [Makefile:296: ggml-cuda/arange.o] Error 1
make: *** [Makefile:296: ggml-cuda/binbcast.o] Error 1
make: *** [Makefile:296: ggml-cuda/clamp.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/mmq.o] Error 1
make: *** [Makefile:296: ggml-cuda/convert.o] Error 1
make: *** [Makefile:296: ggml-cuda/acc.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/concat.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/diagmask.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/argsort.o] Error 1
make: *** [Makefile:296: ggml-cuda/im2col.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/getrows.o] Error 1
make: *** [Makefile:296: ggml-cuda/dmmv.o] Error 1
make: *** [Makefile:296: ggml-cuda/norm.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/pool2d.o] Error 1
make: *** [Makefile:296: ggml-cuda/softmax.o] Error 1
make: *** [Makefile:296: ggml-cuda/rope.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/pad.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/upscale.o] Error 1
make: *** [Makefile:296: ggml-cuda/mmvq.o] Error 1
make: *** [Makefile:296: ggml-cuda/scale.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/quantize.o] Error 1
make: *** [Makefile:296: ggml-cuda/sumrows.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/unary.o] Error 1
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may 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
make: *** [Makefile:296: ggml-cuda/tsembd.o] Error 1
cc: warning: Files\NVIDIA: linker input file unused because linking not done
cc: error: Files\NVIDIA: linker input file not found: No such file or directory
cc: warning: GPU: linker input file unused because linking not done
cc: error: GPU: linker input file not found: No such file or directory
cc: warning: Computing: linker input file unused because linking not done
cc: error: Computing: linker input file not found: No such file or directory
cc: warning: Toolkit\CUDA\v11.7/targets/x86_64-linux/include: linker input file unused because linking not done
cc: error: Toolkit\CUDA\v11.7/targets/x86_64-linux/include: linker input file not found: No such file or directory
make: *** [Makefile:397: ggml-alloc.o] Error 1
cc: warning: Files\NVIDIA: linker input file unused because linking not done
cc: error: Files\NVIDIA: linker input file not found: No such file or directory
cc: warning: GPU: linker input file unused because linking not done
cc: error: GPU: linker input file not found: No such file or directory
cc: warning: Computing: linker input file unused because linking not done
cc: error: Computing: linker input file not found: No such file or directory
cc: warning: Toolkit\CUDA\v11.7/targets/x86_64-linux/include: linker input file unused because linking not done
cc: error: Toolkit\CUDA\v11.7/targets/x86_64-linux/include: linker input file not found: No such file or directory
make: *** [Makefile:400: ggml-backend.o] Error 1
cc: warning: Files\NVIDIA: linker input file unused because linking not done
cc: error: Files\NVIDIA: linker input file not found: No such file or directory
cc: warning: GPU: linker input file unused because linking not done
cc: error: GPU: linker input file not found: No such file or directory
cc: warning: Computing: linker input file unused because linking not done
cc: error: Computing: linker input file not found: No such file or directory
cc: warning: Toolkit\CUDA\v11.7/targets/x86_64-linux/include: linker input file unused because linking not done
cc: error: Toolkit\CUDA\v11.7/targets/x86_64-linux/include: linker input file not found: No such file or directory
make: *** [Makefile:403: ggml-quants.o] Error 1
cc: warning: Files\NVIDIA: linker input file unused because linking not done
cc: error: Files\NVIDIA: linker input file not found: No such file or directory
cc: warning: GPU: linker input file unused because linking not done
cc: error: GPU: linker input file not found: No such file or directory
cc: warning: Computing: linker input file unused because linking not done
cc: error: Computing: linker input file not found: No such file or directory
cc: warning: Toolkit\CUDA\v11.7/targets/x86_64-linux/include: linker input file unused because linking not done
cc: error: Toolkit\CUDA\v11.7/targets/x86_64-linux/include: linker input file not found: No such file or directory
make: *** [Makefile:394: ggml.o] Error 1
c++: warning: Files\NVIDIA: linker input file unused because linking not done
c++: error: Files\NVIDIA: linker input file not found: No such file or directory
c++: warning: GPU: linker input file unused because linking not done
c++: error: GPU: linker input file not found: No such file or directory
c++: warning: Computing: linker input file unused because linking not done
c++: error: Computing: linker input file not found: No such file or directory
c++: warning: Toolkit\CUDA\v11.7/targets/x86_64-linux/include: linker input file unused because linking not done
c++: error: Toolkit\CUDA\v11.7/targets/x86_64-linux/include: linker input file not found: No such file or directory
make: *** [Makefile:408: whisper.o] Error 1