llama.cpp-vulkan
|
b4920-1 |
4 |
1.29
|
Port of Facebook's LLaMA model in C/C++ (with Vulkan GPU optimizations) |
txtsd
|
2025-03-18 21:41 (UTC) |
llama.cpp-cuda-f16
|
b4920-1 |
3 |
1.12
|
Port of Facebook's LLaMA model in C/C++ (with NVIDIA CUDA optimizations and f16) |
txtsd
|
2025-03-18 21:38 (UTC) |
llama.cpp-git
|
b4082.r11.4047be74d-1 |
15 |
1.09
|
Port of Facebook's LLaMA model in C/C++ |
robertfoster
|
2024-11-15 20:30 (UTC) |
llama.cpp-cuda
|
b4920-1 |
6 |
1.04
|
Port of Facebook's LLaMA model in C/C++ (with NVIDIA CUDA optimizations) |
txtsd
|
2025-03-18 21:38 (UTC) |
llama.cpp-sycl-f16
|
b4920-1 |
2 |
0.81
|
Port of Facebook's LLaMA model in C/C++ (with Intel SYCL GPU optimizations and F16) |
txtsd
|
2025-03-18 21:40 (UTC) |
llama.cpp-sycl-f32
|
b4920-1 |
2 |
0.81
|
Port of Facebook's LLaMA model in C/C++ (with Intel SYCL GPU optimizations and F32) |
txtsd
|
2025-03-18 21:41 (UTC) |
llama.cpp
|
b4920-1 |
6 |
0.62
|
Port of Facebook's LLaMA model in C/C++ |
txtsd
|
2025-03-18 21:37 (UTC) |
llama.cpp-hip
|
b4920-1 |
3 |
0.41
|
Port of Facebook's LLaMA model in C/C++ (with AMD ROCm optimizations) |
txtsd
|
2025-03-18 21:39 (UTC) |
jan-bin
|
0.5.15-1 |
9 |
0.28
|
An open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM).(Prebuilt version.Use system-wide electron.) |
zxp19821005
|
2025-02-18 08:30 (UTC) |
python-llama-cpp
|
0.3.8-1 |
2 |
0.19
|
Python bindings for llama.cpp |
envolution
|
2025-03-12 13:00 (UTC) |
llama.cpp-bin
|
b4882-1 |
1 |
0.09
|
LLM inference in C/C++ (precompiled Linux binaries) |
neitsab
|
2025-03-13 15:46 (UTC) |
python-llama-cpp-cuda
|
0.3.8-1 |
0 |
0.00
|
Python bindings for llama.cpp |
envolution
|
2025-03-13 22:55 (UTC) |
llama.cpp-vulkan-git
|
b4730-1 |
0 |
0.00
|
Port of Facebook's LLaMA model in C/C++ (with Vulkan GPU optimizations) |
robertfoster
|
2025-02-16 14:07 (UTC) |
llama.cpp-sycl-f32-git
|
b4082.r11.4047be74d-1 |
0 |
0.00
|
Port of Facebook's LLaMA model in C/C++ (with Intel SYCL GPU optimizations and F32) |
robertfoster
|
2024-11-15 20:37 (UTC) |
llama.cpp-sycl-f16-git
|
b4730-1 |
0 |
0.00
|
Port of Facebook's LLaMA model in C/C++ (with Intel SYCL GPU optimizations and F16) |
robertfoster
|
2025-02-16 14:07 (UTC) |
llama.cpp-service
|
1.1-1 |
0 |
0.00
|
Systemd service files and /etc/ configuration for Llama.cpp Server |
envolution
|
2024-11-26 22:21 (UTC) |
llama.cpp-server-tray
|
0.5-2 |
0 |
0.00
|
Companion system tray app for llama.cpp-server-service |
envolution
|
2024-12-23 01:25 (UTC) |
llama.cpp-hipblas-git
|
b4730-1 |
0 |
0.00
|
Port of Facebook's LLaMA model in C/C++ (with AMD ROCm optimizations) |
robertfoster
|
2025-02-16 14:04 (UTC) |
llama.cpp-cublas-git
|
b4730-1 |
0 |
0.00
|
Port of Facebook's LLaMA model in C/C++ (with NVIDIA CUDA optimizations) |
robertfoster
|
2025-02-16 14:07 (UTC) |
llama.cpp-clblas-git
|
b4730-1 |
0 |
0.00
|
Port of Facebook's LLaMA model in C/C++ (with OpenCL optimizations) |
robertfoster
|
2025-02-16 14:06 (UTC) |