baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Fix for shared library not found and compile issues in Windows (#848)

Browse source 
* fix windows library dll name issue

* Updated README.md Windows instructions

* Update llama_cpp.py to handle different windows dll file versions
This commit is contained in:
Sujeendran Menon 2023-11-02 04:25:57 +05:30 committed by GitHub
parent eefd76fe81
commit 7b136bb5b1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 7 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -92,6 +92,12 @@ Then, call `pip` after setting the variables:
pip install llama-cpp-python pip install llama-cpp-python
``` ```
If you run into issues where it complains it can't find `'nmake'` `'?'` or CMAKE_C_COMPILER, you can extract w64devkit as [mentioned in llama.cpp repo](https://github.com/ggerganov/llama.cpp#openblas) and add those manually to CMAKE_ARGS before running `pip` install:
```ps
$env:CMAKE_GENERATOR = "MinGW Makefiles"
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on -DCMAKE_C_COMPILER=C:/w64devkit/bin/gcc.exe -DCMAKE_CXX_COMPILER=C:/w64devkit/bin/g++.exe"
```
See the above instructions and set `CMAKE_ARGS` to the BLAS backend you want to use. See the above instructions and set `CMAKE_ARGS` to the BLAS backend you want to use.
#### MacOS remarks #### MacOS remarks

1
llama_cpp/llama_cpp.py
View file

@ -42,6 +42,7 @@ def _load_shared_library(lib_base_name: str):
elif sys.platform == "win32": elif sys.platform == "win32":
_lib_paths += [ _lib_paths += [
_base_path / f"{lib_base_name}.dll", _base_path / f"{lib_base_name}.dll",
_base_path / f"lib{lib_base_name}.dll",
] ]
else: else:
raise RuntimeError("Unsupported platform") raise RuntimeError("Unsupported platform")