Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models

Fast parallel LLM inference for MLX

huggingface chat-ui integration with mlx-lm server

Fast parallel LLM inference for MLX

On-the-fly Goliath-style transformer franken-merges with a tiny memory footprint

On-device AI across mobile, embedded and edge for PyTorch

This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

A fast inference library for running LLMs locally on modern consumer-class GPUs

Zero-Shot Speech Editing and Text-to-Speech in the Wild