GGUF
calcuis commited on
Commit
22baa7c
·
verified ·
1 Parent(s): acc7fca

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ building the bundled quantizer requires a C/C++ toolchain and CMake ≥ 3.15
14
  (on Windows: MSVC Build Tools). GPU accelerators are opt-in at build time:
15
 
16
  ```bash
17
- CMAKE_ARGS="-DQUANTIZER_CUDA=ON" pip install gguf-editor # NVIDIA (CUDA toolkit)
18
  CMAKE_ARGS="-DQUANTIZER_HIP=ON" pip install gguf-editor # AMD (ROCm/HIP)
19
  CMAKE_ARGS="-DQUANTIZER_METAL=ON" pip install gguf-editor # Apple (macOS)
20
  ```
 
14
  (on Windows: MSVC Build Tools). GPU accelerators are opt-in at build time:
15
 
16
  ```bash
17
+ CMAKE_ARGS="-DQUANTIZER_CUDA=ON" pip install gguf-editor # NVIDIA (CUDA)
18
  CMAKE_ARGS="-DQUANTIZER_HIP=ON" pip install gguf-editor # AMD (ROCm/HIP)
19
  CMAKE_ARGS="-DQUANTIZER_METAL=ON" pip install gguf-editor # Apple (macOS)
20
  ```