8000 Fixd CUBLAS dll load issue in Windows · abetlen/llama-cpp-python@e9794f9 · GitHub
[go: up one dir, main page]

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

Commit e9794f9

Browse files
committed
Fixd CUBLAS dll load issue in Windows
1 parent 1a13d76 commit e9794f9

File tree

1 file changed

+1
-0
lines changed

1 file changed

+1
-0
lines changed

llama_cpp/llama_cpp.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -48,6 +48,7 @@ def _load_shared_library(lib_base_name: str):
4848
# Add the library directory to the DLL search path on Windows (if needed)
4949
if sys.platform == "win32" and sys.version_info >= (3, 8):
5050
os.add_dll_directory(str(_base_path))
51+
os.add_dll_directory(os.path.join(os.environ["CUDA_PATH"],"bin"))
5152
cdll_args["winmode"] = 0
5253

5354
# Try to load the shared library, handling potential errors

0 commit comments

Comments
 (0)
0