Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,870Apr 18, 2025Updated last year
Alternatives and similar repositories for GRPO-Zero
Users that are interested in GRPO-Zero are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆4,930Oct 27, 2025Updated 8 months ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,228Aug 26, 2025Updated 10 months ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆624Oct 7, 2025Updated 8 months ago
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,582Jan 12, 2025Updated last year
- Minimal reproduction of DeepSeek R1-Zero☆13,182Feb 27, 2026Updated 4 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- A PyTorch native platform for training generative AI models☆5,495Updated this week
- Simple MPI implementation for prototyping or learning☆320Aug 6, 2025Updated 10 months ago
- NanoGPT (124M) in 90 seconds☆5,459Jun 21, 2026Updated last week
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,700Nov 21, 2025Updated 7 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,265Aug 27, 2025Updated 10 months ago
- UNet diffusion model in pure CUDA☆660Jun 28, 2024Updated 2 years ago
- Efficient Triton Kernels for LLM Training☆6,476Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,173Jun 27, 2026Updated last week
- Fully open reproduction of DeepSeek-R1☆26,381Apr 2, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Implementation of Diffusion Transformer (DiT) in JAX☆317Jun 11, 2024Updated 2 years ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,710Jun 17, 2026Updated 2 weeks ago
- Our library for RL environments + evals☆4,254Updated this week
- Train transformer language models with reinforcement learning.☆18,735Updated this week
- Simple RL training for reasoning☆3,867Dec 23, 2025Updated 6 months ago
- LLM training in simple, raw C/CUDA☆30,362Jun 26, 2025Updated last year
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆151Nov 11, 2024Updated last year
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,598Jul 1, 2024Updated 2 years ago
- LLM101n: Let's build a Storyteller☆37,383Aug 1, 2024Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Fast and memory-efficient exact attention☆24,304Updated this week
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆351Nov 2, 2025Updated 8 months ago
- Democratizing Reinforcement Learning for LLMs☆5,677Updated this week
- s1: Simple test-time scaling☆6,658Jun 25, 2025Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆60,304Nov 12, 2025Updated 7 months ago
- Schedule-Free Optimization in PyTorch☆2,310Jun 18, 2026Updated 2 weeks ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆965Nov 16, 2025Updated 7 months ago
- Frontier Models playing the board game Diplomacy.☆676Jun 1, 2026Updated last month
- The official PyTorch implementation of Google's Gemma models☆5,703May 30, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,229Aug 22, 2025Updated 10 months ago
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,385May 7, 2026Updated last month
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,838May 11, 2025Updated last year
- 🚀 Efficient implementations for emerging model architectures☆5,279Updated this week
- Minimalistic large language model 3D-parallelism training☆2,737May 26, 2026Updated last month
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,761Jul 18, 2025Updated 11 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆84,877Updated this week