Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,781Apr 18, 2025Updated 10 months ago
Alternatives and similar repositories for GRPO-Zero
Users that are interested in GRPO-Zero are comparing it to the libraries listed below
Sorting:
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆4,668Oct 27, 2025Updated 4 months ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,090Aug 26, 2025Updated 6 months ago
- Minimal reproduction of DeepSeek R1-Zero☆12,853Updated this week
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆597Oct 7, 2025Updated 4 months ago
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,550Jan 12, 2025Updated last year
- A PyTorch native platform for training generative AI models☆5,098Updated this week
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,219Aug 27, 2025Updated 6 months ago
- NanoGPT (124M) in 2 minutes☆4,679Updated this week
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,593Nov 21, 2025Updated 3 months ago
- Fully open reproduction of DeepSeek-R1☆25,910Nov 24, 2025Updated 3 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆19,519Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,037Feb 21, 2026Updated last week
- Efficient Triton Kernels for LLM Training☆6,162Updated this week
- UNet diffusion model in pure CUDA☆657Jun 28, 2024Updated last year
- Simple RL training for reasoning☆3,830Dec 23, 2025Updated 2 months ago
- Implementation of Diffusion Transformer (DiT) in JAX☆306Jun 11, 2024Updated last year
- Simple MPI implementation for prototyping or learning☆303Aug 6, 2025Updated 6 months ago
- Train transformer language models with reinforcement learning.☆17,460Updated this week
- Our library for RL environments + evals☆3,869Updated this week
- LLM training in simple, raw C/CUDA☆28,993Jun 26, 2025Updated 8 months ago
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,329Jul 1, 2024Updated last year
- Democratizing Reinforcement Learning for LLMs☆5,167Updated this week
- Fast and memory-efficient exact attention☆22,361Updated this week
- LLM101n: Let's build a Storyteller☆36,390Aug 1, 2024Updated last year
- s1: Simple test-time scaling☆6,636Jun 25, 2025Updated 8 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆53,743Nov 12, 2025Updated 3 months ago
- Schedule-Free Optimization in PyTorch☆2,257May 21, 2025Updated 9 months ago
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆146Nov 11, 2024Updated last year
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,024Nov 4, 2025Updated 3 months ago
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,752Jul 18, 2025Updated 7 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,428Updated this week
- A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes…☆4,167Jan 5, 2026Updated last month
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,184Aug 22, 2025Updated 6 months ago
- The official PyTorch implementation of Google's Gemma models☆5,606May 30, 2025Updated 9 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,739May 11, 2025Updated 9 months ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆952Nov 16, 2025Updated 3 months ago
- Official PyTorch implementation for "Large Language Diffusion Models"☆3,609Nov 12, 2025Updated 3 months ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆335Nov 2, 2025Updated 4 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆71,234Updated this week