vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs featuring PagedAttention.
AT A GLANCE
A high-throughput and memory-efficient inference and serving engine for LLMs featuring PagedAttention.
KEEP EXPLORING
Website snapshot
ollama/ollama
Run, customize, and bundle Llama 3, Mistral, Gemma, and custom models locally via simple CLI or OpenAI-compatible API.
git clone https://github.com/ollama/ollama.git
Repository preview
janhq/jan
Turn your computer into an AI machine. 100% offline, local-first alternative to ChatGPT with support for local GGUF models.
git clone https://github.com/janhq/jan.git
Repository preview
invoke-ai/InvokeAI
A leading creative engine for Stable Diffusion, FLUX, and open generative art models with unified canvas and batch generation.
git clone https://github.com/invoke-ai/InvokeAI.git
Short demos. New discoveries. Less noise in your feed.