Merge branch 'main' of github.com:abetlen/llama_cpp_python into main

llama_cpp/llama_cpp.py

@@ -48,6 +48,7 @@ def _load_shared_library(lib_base_name: str):
     # Add the library directory to the DLL search path on Windows (if needed)
     if sys.platform == "win32" and sys.version_info >= (3, 8):
         os.add_dll_directory(str(_base_path))
+        os.add_dll_directory(os.path.join(os.environ["CUDA_PATH"],"bin"))
         cdll_args["winmode"] = 0
 
     # Try to load the shared library, handling potential errors