#
Starred repositories
This API provides programmatic access to the AlphaGenome model developed by Google DeepMind.
Efficient Triton Kernels for LLM Training
ByteCheckpoint: An Unified Checkpointing Library for LFMs
Distributed Compiler based on Triton for Parallel Systems
🌐 WebAgent for Information Seeking bulit by Tongyi Lab: WebWalker & WebDancer & WebSailor
Reverse Engineering Gemma 3n: Google's New Edge-Optimized Language Model
Scalable toolkit for efficient model alignment
Py D696 torch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI
Democratizing Reinforcement Learning for LLMs
Understanding R1-Zero-Like Training: A Critical Perspective
An Open-source RL System from ByteDance Seed and Tsinghua AIR
A PyTorch native platform for training generative AI models
Fully open reproduction of DeepSeek-R1
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
PyTorch building blocks for the OLMo ecosystem
Everything about the SmolLM2 and SmolVLM family of models
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.
Latest Advances on System-2 Reasoning
SpargeAttention: A training-free sparse attention that can accelerate any model inference.
DeepEP: an efficient expert-parallel communication library
Dynamic Memory Management for Serving LLMs without PagedAttention
FlashMLA: Efficient MLA decoding kernels
Official Repo for Open-Reasoner-Zero
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.