Package Details: llama.cpp-cuda-f16 b5581-1

Git Clone URL: https://aur.archlinux.org/llama.cpp-cuda-f16.git (read-only, click to copy)
Package Base: llama.cpp-cuda-f16
Description: Port of Facebook's LLaMA model in C/C++ (with NVIDIA CUDA optimizations and f16)
Upstream URL: https://github.com/ggerganov/llama.cpp
Licenses: MIT
Conflicts: libggml, llama.cpp
Provides: llama.cpp
Submitter: txtsd
Maintainer: txtsd
Last Packager: txtsd
Votes: 3
Popularity: 0.21
First Submitted: 2024-12-06 13:35 (UTC)
Last Updated: 2025-06-03 01:13 (UTC)

Latest Comments

v1993 commented on 2024-12-27 22:05 (UTC)

Thank you for making this one! It's nice to have.

txtsd commented on 2024-12-06 14:15 (UTC)

Alternate versions

llama.cpp
llama.cpp-vulkan
llama.cpp-sycl-fp16
llama.cpp-sycl-fp32
llama.cpp-cuda
llama.cpp-cuda-f16
llama.cpp-hip