Detected CUDA files, patching ldflags
Emitting ninja build file /home/ravindu.nagasinghe/.cache/torch_extensions/py38_cu118/fused_adam/build.ninja...
Building extension module fused_adam...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/2] /usr/bin/nvcc -DTORCH_EXTENSION_NAME=fused_adam -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="gcc" -DPYBIND11_STDLIB="libstdcpp" -DPYBIND11_BUILD_ABI="cxxabi1011" -I/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/ops/csrc/includes -I/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/ops/csrc/adam -isystem /home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/include -isystem /home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/include/TH -isystem /home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/include/THC -isystem /home/ravindu.nagasinghe/.conda/envs/videomae/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS_ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_80,code=compute_80 -gencode=arch=compute_80,code=sm_80 --compiler-options '-fPIC' -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -lineinfo --use_fast_math -gencode=arch=compute_80,code=sm_80 -gencode=arch=compute_80,code=compute_80 -DBF16_AVAILABLE -std=c++17 -c /home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/ops/csrc/adam/multi_tensor_adam.cu -o multi_tensor_adam.cuda.o
FAILED: multi_tensor_adam.cuda.o
/usr/bin/nvcc -DTORCH_EXTENSION_NAME=fused_adam -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="gcc" -DPYBIND11_STDLIB="libstdcpp" -DPYBIND11_BUILD_ABI="cxxabi1011" -I/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/ops/csrc/includes -I/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/ops/csrc/adam -isystem /home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/include -isystem /home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/include/TH -isystem /home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/include/THC -isystem /home/ravindu.nagasinghe/.conda/envs/videomae/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS_ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_80,code=compute_80 -gencode=arch=compute_80,code=sm_80 --compiler-options '-fPIC' -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -lineinfo --use_fast_math -gencode=arch=compute_80,code=sm_80 -gencode=arch=compute_80,code=compute_80 -DBF16_AVAILABLE -std=c++17 -c /home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/ops/csrc/adam/multi_tensor_adam.cu -o multi_tensor_adam.cuda.o
ERROR: No supported gcc/g++ host compiler found.
Use 'nvcc -ccbin ' to specify a host compiler.
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
File "/home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1893, in _run_ninja_build
subprocess.run(
File "/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/subprocess.py", line 516, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "run_class_finetuning.py", line 927, in
main(opts, ds_init)
File "run_class_finetuning.py", line 727, in main
model, optimizer, _, _ = ds_init(
File "/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/init.py", line 171, in initialize
engine = DeepSpeedEngine(args=args,
File "/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/runtime/engine.py", line 303, in init
self._configure_optimizer(optimizer, model_parameters)
File "/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/runtime/engine.py", line 1202, in _configure_optimizer
basic_optimizer = self._configure_basic_optimizer(model_parameters)
File "/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/runtime/engine.py", line 1264, in _configure_basic_optimizer
optimizer = FusedAdam(
File "/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/ops/adam/fused_adam.py", line 94, in init
fused_adam_cuda = FusedAdamBuilder().load()
File "/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/ops/op_builder/builder.py", line 446, in load
return self.jit_load(verbose)
File "/home/ravindu.nagasinghe/.conda/envs/videomae/lib/python3.8/site-packages/deepspeed/ops/op_builder/builder.py", line 489, in jit_load
op_module = load(name=self.name,
File "/home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1284, in load
return _jit_compile(
File "/home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1509, in _jit_compile
_write_ninja_file_and_build_library(
File "/home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1624, in _write_ninja_file_and_build_library
_run_ninja_build(
File "/home/ravindu.nagasinghe/.local/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1909, in _run_ninja_build
raise RuntimeError(message) from e
RuntimeError: Error building extension 'fused_adam'