Open ikionchiu opened 2 months ago
Have you tried checking the directory that the llama_cpp is in? On linux machines the name of the .so file is libllama.so, but on windows machines where the file is a .dll, the names are llama.dll and llava.dll. You could try the following code and check if it works: _lib_path = 'D:/temp/test/llama_cpp/llama.dll'
Prerequisites
Please answer the following questions for yourself before submitting an issue.
Expected Behavior
Current Behavior
Environment and Context
Physical hardware i am using:
SDK version(The CMake and MinGW folders were copied from CLion and added separately to the environment variables):
Steps to Reproduce
step 1: Create env folder and placed in the same directory level as llama-cpp-python.
step 2: Copy the CMake and MinGW folders from CLion directory and add to the env folder.
step 3: Add CMake and MinGW to the system environment variables.(cmake:
***\env\cmake\win\x64\bin
; mingw:***\env\mingw\bin
)step 4:
cd llama-cpp-python
step 5:
mkdir build
step 6:
cd build
step 7:
cmake .. -DBUILD_SHARED_LIBS=ON -G "MinGW Makefiles"
step 8:
cmake --build . --config Release
step 9: Then, I can find the libllama.dll file in the directory
***\llama-cpp-python\build\bin\
.step 10: Then, I copied the generated libllama.dll to another directory for testing, but the test failed. I pinpointed the issue to the following code:
Failure Logs
The ERROR log as following: