You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -99,7 +99,7 @@ when you can't use the precompiled binary directly, we provide an automated buil
99
99
- You can attempt a CuBLAS build with `LLAMA_CUBLAS=1`, (or `LLAMA_HIPBLAS=1` for AMD). You will need CUDA Toolkit installed. Some have also reported success with the CMake file, though that is more for windows.
100
100
- For a full featured build (all backends), do `make LLAMA_CLBLAST=1 LLAMA_CUBLAS=1 LLAMA_VULKAN=1`. (Note that `LLAMA_CUBLAS=1` will not work on windows, you need visual studio)
101
101
- To make your build sharable and capable of working on other devices, you must use `LLAMA_PORTABLE=1`
102
-
- After all binaries are built, you can run the python script with the command `koboldcpp.py [ggml_model.gguf] [port]`
102
+
- After all binaries are built, you can run the python script with the command `python koboldcpp.py [ggml_model.gguf] [port]`
103
103
104
104
### Compiling on Windows
105
105
- You're encouraged to use the .exe released, but if you want to compile your binaries from source at Windows, the easiest way is:
@@ -123,7 +123,7 @@ when you can't use the precompiled binary directly, we provide an automated buil
123
123
- A makefile is provided, simply run `make`.
124
124
- If you want Metal GPU support, instead run `make LLAMA_METAL=1`, note that MacOS metal libraries need to be installed.
125
125
- To make your build sharable and capable of working on other devices, you must use `LLAMA_PORTABLE=1`
126
-
- After all binaries are built, you can run the python script with the command `koboldcpp.py --model [ggml_model.gguf]` (and add `--gpulayers (number of layer)` if you wish to offload layers to GPU).
126
+
- After all binaries are built, you can run the python script with the command `python koboldcpp.py --model [ggml_model.gguf]` (and add `--gpulayers (number of layer)` if you wish to offload layers to GPU).
127
127
128
128
### Compiling on Android (Termux Installation)
129
129
-[First, Install and run Termux from F-Droid](https://f-droid.org/en/packages/com.termux/)
@@ -152,7 +152,7 @@ and it will install everything required. Alternatively, you can download the abo
152
152
153
153
## AMD Users
154
154
- For most users, you can get very decent speeds by selecting the **Vulkan** option instead, which supports both Nvidia and AMD GPUs.
155
-
- Alternatively, you can try the ROCM fork at https://github.com/YellowRoseCx/koboldcpp-rocm
155
+
- Alternatively, you can try the ROCM fork at https://github.com/YellowRoseCx/koboldcpp-rocm though this may be outdated.
156
156
157
157
## Third Party Resources
158
158
- These unofficial resources have been contributed by the community, and may be outdated or unmaintained. No official support will be provided for them!
0 commit comments