caffe2-cuda : A deep learning framework (CUDA backend) ( https://pytorch.org/ )
caffe2-rocm : A deep learning framework (ROCm backend) ( https://pytorch.org/ )
ik_llama-cpp : llama.cpp fork with additional SOTA quants and improved performance ( https://github.com/ikawrakow/ik_llama.cpp )
llama-cpp : LLM inference in C/C++ (GGML/GGUF) — CPU + optional GPU backends ( https://github.com/ggml-org/llama.cpp )
ollama : Get up and running with large language models. ( https://ollama.com )
pytorch-cuda : Tensors and Dynamic neural networks in Python (CUDA backend) ( https://pytorch.org/ )
pytorch-rocm : Tensors and Dynamic neural networks in Python (ROCm backend) ( https://pytorch.org/ )
segment-anything : Meta AI Segment Anything Model (SAM) ( https://github.com/facebookresearch/segment-anything )
stable-diffusion-cpp : Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++ ( https://github.com/leejet/stable-diffusion.cpp )
torchaudio-cuda : Audio processing for PyTorch (CUDA backend) ( https://github.com/pytorch/audio )
torchaudio-rocm : Audio processing for PyTorch (ROCm backend) ( https://github.com/pytorch/audio )
torchvision-cuda : Datasets, transforms and models for computer vision (CUDA backend) ( https://github.com/pytorch/vision )
torchvision-rocm : Datasets, transforms and models for computer vision (ROCm backend) ( https://github.com/pytorch/vision )
ultralytics : Ultralytics YOLO — object detection, segmentation, classification ( https://github.com/ultralytics/ultralytics )
Pour rajouter une e-build dans l'arbre de portage :
L'ebuild est alors rajouté dans l'arbre de portage.
Vous pouvez aussi utiliser layman : emerge layman puis layman -a zGentoo
Pour Paludis utilisez ce rsync : rsync://gentoo.zugaina.org/zGentoo-portage
En cas de problèmes : ycarus(-at-)zugaina.org