maociao
diff --git a/‎README.md
Copy file name to clipboardExpand all lines: README.md
+6Lines changed: 6 additions & 0 deletions b/‎README.md
Copy file name to clipboardExpand all lines: README.md
+6Lines changed: 6 additions & 0 deletions
diff --git a/‎llama_cpp/llama_cpp.py
Copy file name to clipboardExpand all lines: llama_cpp/llama_cpp.py
+1Lines changed: 1 addition & 0 deletions b/‎llama_cpp/llama_cpp.py
Copy file name to clipboardExpand all lines: llama_cpp/llama_cpp.py
+1Lines changed: 1 addition & 0 deletions
@@ -92,6 +92,12 @@ Then, call `pip` after setting the variables:
 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.
 
 #### MacOS remarks
 
@@ -42,6 +42,7 @@ def _load_shared_library(lib_base_name: str):
     elif sys.platform == "win32":
         _lib_paths += [
             _base_path / f"{lib_base_name}.dll",
+            _base_path / f"lib{lib_base_name}.dll",
         ]
     else:
         raise RuntimeError("Unsupported platform")
Original file line number	Diff line number	Diff line change
`@@ -42,6 +42,7 @@ def _load_shared_library(lib_base_name: str):`
`42`	`42`	`elif sys.platform == "win32":`
`43`	`43`	`_lib_paths += [`
`44`	`44`	`_base_path / f"{lib_base_name}.dll",`
	`45`	`+ _base_path / f"lib{lib_base_name}.dll",`
`45`	`46`	`]`
`46`	`47`	`else:`
`47`	`48`	`raise RuntimeError("Unsupported platform")`