search

AmericanPresidentJimmyCarter / yal-discord-bot

Yet Another LLaMA/ALPACA Discord Bot
Other
72 stars 1 forks source link

CUDA Compilation error. Any chance to upload compiled ? #4

Open progressionnetwork opened 1 year ago

progressionnetwork commented 1 year ago

D:\BLLaMA\venv\lib\site-packages\torch\include\pybind11\cast.h(1429): error: too few arguments for template template parameter "Tuple" detected during instantiation of class "pybind11::detail::tuple_caster<Tuple, Ts...> [with Tuple=std::pair, Ts=<T1, T2>]" (1507): here

D:\BLLaMA\venv\lib\site-packages\torch\include\pybind11\cast.h(1503): error: too few arguments for template template parameter "Tuple" detected during instantiation of class "pybind11::detail::tuple_caster<Tuple, Ts...> [with Tuple=std::pair, Ts=<T1, T2>]" (1507): here

2 errors detected in the compilation of "quant_cuda_kernel.cu". error: command 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.5\bin\nvcc.exe' failed with exit code 1

AmericanPresidentJimmyCarter commented 1 year ago

I think it would be CUDA version specific. I am compiling on 11.7. You could try a docker in WSL2 with a later CUDA toolkit version.