Repository Showcase
A curated collection of interesting GitHub repositories
ModelCloud/GPTQModel
Model quantization with hardware acceleration for Nvidia, AMD, and Intel
Related repos
- competes to train GPT-2 models super fast on 8xH100 GPUs using speedrun benchmarks
- open-source GPU cluster manager for AI models
- open-weight GPT models for reasoning and agent tasks
- Run 70B LLMs on a 4GB GPU with layer-wise inference and memory optimization, quantization optional
- AI inference engine for Apple Silicon, hybrid GPU/MPSGraph, easy model support
- Python framework for fast GPU simulation and graphics
- semantic cache for LLM queries, speeds up GPT apps, cuts API costs
- run local LLMs fast on consumer GPUs with flexible quantization
- tensor library for machine learning with support for hardware acceleration and model inference
- GGUF quantization nodes for running ComfyUI models on low-end GPUs
