Build error
Opened this issue · 1 comments
MoffKalast commented
Running make after cloning seems to result in the following:
~/llama3.cuda$ make
nvcc -DUSE_CUBLAS=1 -g -o runcuda llama3.cu -lm -lcublas
/usr/include/c++/11/bits/std_function.h:435:145: error: parameter packs not expanded with ‘...’:
435 | function(_Functor&& __f)
| ^
/usr/include/c++/11/bits/std_function.h:435:145: note: ‘_ArgTypes’
/usr/include/c++/11/bits/std_function.h:530:146: error: parameter packs not expanded with ‘...’:
530 | operator=(_Functor&& __f)
| ^
/usr/include/c++/11/bits/std_function.h:530:146: note: ‘_ArgTypes’
make: *** [Makefile:7: runcuda] Error 1
Ubuntu 22.04, Make 4.3, CUDA 12.2 (at least according to nvidia-smi). Llama.cpp with CuBLAS compiles fine on the same system so it should be all set up correctly in theory.
likejazz commented
As you can see, the error is not coming from my code, but from somewhere else. Try checking the version of your nvcc
compiler.