slime is an LLM post-training framework for RL Scaling.

Fully Open Framework for Democratized Multimodal Training

SGLang is a fast serving framework for large language models and vision language models.

Ephemeral github runners in docker

Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"

Python sample project for trying out Dev Containers

Distributed RL System for LLM Reasoning

Witness the aha moment of VLM with less than $3.

A python wrapper to extract text from images on a mac system. Uses the vision framework from Apple.

🐺 Wolf: Captioning Everything with a World Summarization Framework

VILA - A multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.