Search:

sci-misc/llama-cpp

Port of Facebook's LLaMA model in C/C++

sci-ml/ollama

Get up and running with Llama 3, Mistral, Gemma, and other language models.

app-misc/ollama-bin

Get up and running with local large language models

app-misc/lmstudio-bin

LM Studio – Local LLM desktop app (binary .deb repack)

sci-ml/ollama-bin

Get up and running with Llama 3, Mistral, Gemma, and other language models

dev-python/jax

Differentiate, compile, and transform Numpy code

sci-libs/libxc

A library of exchange-correlation functionals for use in DFT

sys-apps/hwloc

Displays the hardware topology in convenient formats

sys-block/libfabric

The Open Fabrics Interfaces (OFI) framework

dev-debug/gdb

GNU debugger

llvm-runtimes/openmp

OpenMP runtime libraries for LLVM/clang compiler

sci-ml/caffe2

A deep learning framework

sci-ml/gloo

library of floating-point neural network inference operators

sci-ml/kineto

part of the PyTorch Profiler

sci-ml/pytorch

Tensors and Dynamic neural networks in Python

sci-ml/torchvision

Datasets, transforms and models to specific to computer vision

sci-ml/llama-cpp

LLM inference in C/C++

sci-ml/ggml

Tensor library for machine learning

sci-ml/torchaudio

Data manipulation and transformation for audio signal processing

dev-python/cupy

CuPy: A NumPy-compatible array library accelerated by CUDA

sci-libs/torchaudio

Data manipulation and transformation for audio signal processing

sci-ml/flash-attn

Flash Attention: Fast and Memory-Efficient Exact Attention (Python component).

sci-misc/ik_llama-cpp

llama.cpp fork with additional SOTA quants and improved performance

sci-misc/stable-diffusion-cpp

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

dev-python/tensorflow-io-gcs-filesystem-nightly

TensorFlow IO [wheel]

dev-python/tensorflow-io-nightly

TensorFlow IO [wheel]

dev-python/comfy-aimdo

AI Model Dynamic Offloader for ComfyUI

media-gfx/comfyui

The most powerful and modular diffusion model GUI and backend

dev-python/vllm

High-throughput, memory-efficient inference and serving engine for LLMs

sci-ml/lemonade

Local AI server: optimized LLM inference on AMD NPU + GPU

dev-python/tilelang

Tile-level programming language for high-performance ML kernels

sci-ml/torchcodec

Media decoding for PyTorch, the torchaudio IO backend

sci-ml/ik_llama-cpp

llama.cpp fork with additional SOTA quants and improved performance

sci-ml/stable-diffusion-cpp

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

virtual/caffe2

Virtual for caffe2/PyTorch backend

virtual/pytorch

Virtual for PyTorch Python bindings

virtual/comfyui

Virtual for ComfyUI diffusion model GUI

sci-ml/bitsandbytes

k-bit quantization (QLoRA) and 8-bit optimizers for PyTorch

sci-ml/colibri

Run GLM-5.2 (744B MoE) on consumer hardware with expert streaming

sci-ml/koboldcpp

All-in-one local AI server (LLM, image, speech, TTS) on ggml/llama.cpp

app-local-ai/depth-anything

LocalAI depth-estimation backend (depth-anything.cpp gRPC server)

app-local-ai/crispasr

LocalAI speech backend (CrispASR gRPC server)

app-local-ai/llama-cpp

LocalAI text-generation backend (llama.cpp gRPC server)

app-local-ai/vibevoice-cpp

LocalAI text-to-speech backend (vibevoice.cpp gRPC server)

app-local-ai/stablediffusion-ggml

LocalAI image-generation backend (stable-diffusion.cpp gRPC server)

app-local-ai/whisper

LocalAI speech-to-text backend (whisper.cpp gRPC server)

app-local-ai/parakeet-cpp

LocalAI speech-to-text backend (parakeet.cpp gRPC server)

app-local-ai/rfdetr-cpp

LocalAI object-detection backend (rf-detr.cpp gRPC server)

app-local-ai/qwen3-tts-cpp

LocalAI text-to-speech backend (qwentts.cpp gRPC server)

app-local-ai/bonsai

LocalAI text-generation backend for 1-bit/ternary models (Bonsai fork of llama.cpp)