Update README.md
Browse files
README.md
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
tags:
|
4 |
-
- llama-cpp-python,
|
5 |
-
- cuda,
|
6 |
-
- gemma
|
7 |
-
- gemma-3,
|
8 |
-
- windows,
|
9 |
-
- wheel,
|
10 |
-
- prebuilt,
|
11 |
-
- .whl,
|
12 |
-
- local-llm,
|
13 |
-
---
|
14 |
# llama-cpp-python Prebuilt Wheel (Windows x64, CUDA 12.8, Gemma 3 Support)
|
15 |
|
16 |
---
|
@@ -125,9 +125,9 @@ Confirmation that your GPU(s) are being used for model layer offloading.
|
|
125 |
Once installed and verified, you can use llama-cpp-python in your projects as you normally would. Refer to the official llama-cpp-python documentation for detailed usage instructions.
|
126 |
|
127 |
## Acknowledgments
|
128 |
-
This prebuilt wheel is based on the excellent llama-cpp-python project by Andrei Betlen (@abetlen). All credit for the core library and Python bindings goes to the original maintainers and to llama.cpp by Georgi Gerganov (@ggerganov).
|
129 |
|
130 |
-
This specific wheel was built by Bernard Peter Fitzgerald (@
|
131 |
|
132 |
## License
|
133 |
This prebuilt wheel is distributed under the MIT License, the same license as the original llama-cpp-python project.
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- llama-cpp-python,
|
5 |
+
- cuda,
|
6 |
+
- gemma
|
7 |
+
- gemma-3,
|
8 |
+
- windows,
|
9 |
+
- wheel,
|
10 |
+
- prebuilt,
|
11 |
+
- .whl,
|
12 |
+
- local-llm,
|
13 |
+
---
|
14 |
# llama-cpp-python Prebuilt Wheel (Windows x64, CUDA 12.8, Gemma 3 Support)
|
15 |
|
16 |
---
|
|
|
125 |
Once installed and verified, you can use llama-cpp-python in your projects as you normally would. Refer to the official llama-cpp-python documentation for detailed usage instructions.
|
126 |
|
127 |
## Acknowledgments
|
128 |
+
This prebuilt wheel is based on the excellent llama-cpp-python project by Andrei Betlen (@abetlen). All credit for the core library and Python bindings goes to the original maintainers and to llama.cpp by Georgi Gerganov (@ggerganov) and the ggml team.
|
129 |
|
130 |
+
This specific wheel was built by Bernard Peter Fitzgerald (@boneylizardwizard) using the source code from abetlen/llama-cpp-python, compiled with CUDA 12.8 support for Windows x64 systems, and verified for Gemma 3 model compatibility.
|
131 |
|
132 |
## License
|
133 |
This prebuilt wheel is distributed under the MIT License, the same license as the original llama-cpp-python project.
|