Autoresearch for Go

The agent that grows with you

cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign languag…

An autonomous novel writing pipeline, by Hermes Agent

how to optimize some algorithm in cuda.

My learning notes for ML SYS.

Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models

The paper list of "Memory in the Age of AI Agents: A Survey"

A simple, performant and scalable JAX-based world modeling codebase.

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

High-performance C++ utilities

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Reinforcing General Reasoning without Verifiers

Public code to accompany Low Probability Estimation paper.

Accelerate LLM preference tuning via prefix sharing with a single line of code

LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

s1: Simple test-time scaling

TOPLOC: is a novel method for verifiable inference that enables users to verify that LLM providers are using the correct model configurations and settings

A zero-dependency ML framework in C with a modern Python API for full control over execution and memory.

[ICLR2025] DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models

An app that brings language models directly to your phone.

Use your Neovim like using Cursor AI IDE!

Dynamic Memory Management for Serving LLMs without PagedAttention

Refine high-quality datasets and visual AI models

A torch-based, universal tensor-parallel library.

Efficient Triton Kernels for LLM Training