Democratizing Reinforcement Learning for LLMs

🐵 Preswald is a full-stack platform for building, deploying, and managing interactive data applications. It brings ingestion, storage, transformation, and visualization into a simple SDK, minimizin…

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Ongoing research training transformer models at scale

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

Ultra | Ultimate | Unified CCL

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

veRL: Volcano Engine Reinforcement Learning for LLM

Scalable RL solution for advanced reasoning of language models

Large Reasoning Models

Code for the paper 🌳 Tree Search for Language Model Agents

[ICML 2024] Official repository for "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"

Official repo for paper DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.

Google Research

LLM verified with Monte Carlo Tree Search

Optimizing inference proxy for LLMs

Build resilient language agents as graphs.

A throughput-oriented high-performance serving framework for LLMs

Automating enterprise workflows with multimodal agents

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

Large Context Attention

Visual Studio Code

VS Code in the browser

[OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.