Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,821Apr 18, 2025Updated 11 months ago
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.☆4,801Oct 27, 2025Updated 5 months ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,146Aug 26, 2025Updated 7 months ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆606Oct 7, 2025Updated 6 months ago
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,563Jan 12, 2025Updated last year
- Minimal reproduction of DeepSeek R1-Zero☆13,038Feb 27, 2026Updated last month
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A PyTorch native platform for training generative AI models☆5,220Updated this week
- Simple MPI implementation for prototyping or learning☆309Aug 6, 2025Updated 8 months ago
- NanoGPT (124M) in 2 minutes☆5,070Mar 29, 2026Updated 2 weeks ago
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,639Nov 21, 2025Updated 4 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,241Aug 27, 2025Updated 7 months ago
- UNet diffusion model in pure CUDA☆657Jun 28, 2024Updated last year
- Efficient Triton Kernels for LLM Training☆6,265Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMs☆20,603Updated this week
- Fully open reproduction of DeepSeek-R1☆25,973Apr 2, 2026Updated last week
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Implementation of Diffusion Transformer (DiT) in JAX☆311Jun 11, 2024Updated last year
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,340Updated this week
- Our library for RL environments + evals☆3,986Updated this week
- Train transformer language models with reinforcement learning.☆17,967Apr 7, 2026Updated last week
- Simple RL training for reasoning☆3,846Dec 23, 2025Updated 3 months ago
- LLM training in simple, raw C/CUDA☆29,511Jun 26, 2025Updated 9 months ago
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,417Jul 1, 2024Updated last year
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆148Nov 11, 2024Updated last year
- LLM101n: Let's build a Storyteller☆36,742Aug 1, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆343Nov 2, 2025Updated 5 months ago
- Fast and memory-efficient exact attention☆23,344Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,402Updated this week
- s1: Simple test-time scaling☆6,640Jun 25, 2025Updated 9 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆56,599Nov 12, 2025Updated 5 months ago
- Schedule-Free Optimization in PyTorch☆2,271May 21, 2025Updated 10 months ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆956Nov 16, 2025Updated 4 months ago
- Frontier Models playing the board game Diplomacy.☆645Feb 11, 2026Updated 2 months ago
- The official PyTorch implementation of Google's Gemma models☆5,655May 30, 2025Updated 10 months ago
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,194Aug 22, 2025Updated 7 months ago
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,185Nov 4, 2025Updated 5 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,782May 11, 2025Updated 11 months ago
- 🚀 Efficient implementations for emerging model architectures☆4,878Updated this week
- Minimalistic large language model 3D-parallelism training☆2,644Apr 7, 2026Updated last week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,755Jul 18, 2025Updated 8 months ago
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,620Sep 10, 2025Updated 7 months ago