Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions data/reusables/copilot/llama-cpp-windows-install.md
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ To install llama.cpp on Windows with the CUDA build:
mkdir "%LOCALAPPDATA%\Programs\llama.cpp\BUILD-cuda-13.4-arm64"
```

Replacing `BUILD` the the build number—for example, `b11803`.
Replacing `BUILD` with the build number—for example, `b11803`.

1. Extract all files from both ZIP files directly into this folder. If you use **Extract All** in File Explorer, change the destination to this folder, because by default File Explorer creates a separate subfolder for each ZIP file. When you're done, the folder should contain a large number of files, including `llama-server.exe`, `cudart64_13.dll`, `cublas64_13.dll`, and `cublasLt64_13.dll`, with no subfolders.
1. Set the `LLAMACPP_SERVER_PATH` environment variable:
Expand All @@ -22,7 +22,7 @@ To install llama.cpp on Windows with the CUDA build:
setx LLAMACPP_SERVER_PATH "%LOCALAPPDATA%\Programs\llama.cpp\BUILD-cuda-13.4-arm64\llama-server.exe"
```

Replacing `BUILD` the the build number.
Replacing `BUILD` with the build number.

1. Close Command Prompt and open a new Command Prompt window. If the {% data variables.copilot.github_copilot_app_short %} or {% data variables.product.prodname_vscode_shortname %} is already open, restart it. If {% data variables.copilot.copilot_cli_short %} is running, exit it and start it again from a new terminal window.
1. To check the installation, run:
Expand Down
Loading