Simple high-throughput inference library

🤗 Benchmark Large Language Models Reliably On Your Data

This is the official code for the paper: Robust Utility-Preserving Text Anonymization Based on Large Language Models

CursorCore: Assist Programming through Aligning Anything

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

A repository to unravel the language of GPUs, making their kernel conversations easy to understand

[ICLR 2025] "Training LMs on Synthetic Edit Sequences Improves Code Synthesis" (Piterbarg, Pinto, Fergus)

[ICLR 2025] 🚀 CodeMMLU Evaluator: A framework for evaluating LM models on CodeMMLU MCQs benchmark.

Diffusion on syntax trees for program synthesis

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Inference-time scaling for LLMs-as-a-judge.

Code for ICML 2025 paper | Joint Localization and Activation Editing for Low-Resource Fine-Tuning

verl: Volcano Engine Reinforcement Learning for LLMs

[NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898

🤖 Headless IDE for AI agents

LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

[ICML 2025 Oral] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Machine Learning Engineering Open Book

Code for studying the super weight in LLM

📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools lik…

[ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)

CodeGate: Security, Workspaces and Multiplexing for AI Agentic Frameworks

Privacy-Preserving Prompt Tuning for Large Language Model