Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,896Apr 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:
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,702Nov 21, 2025Updated 8 months ago
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆4,984Oct 27, 2025Updated 9 months ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,280Aug 26, 2025Updated 11 months ago
- Simple MPI implementation for prototyping or learning☆327Aug 6, 2025Updated last year
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆358Nov 2, 2025Updated 9 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- NanoGPT (124M) in 90 seconds☆5,666Updated this week
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆630Oct 7, 2025Updated 10 months ago
- Minimal reproduction of DeepSeek R1-Zero☆13,226Feb 27, 2026Updated 5 months ago
- Our library for RL environments + evals☆4,507Updated this week
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,594Jan 12, 2025Updated last year
- A PyTorch native platform for training generative AI models☆5,621Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,949Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,908Updated this week
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,271Aug 27, 2025Updated 11 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Train transformer language models with reinforcement learning.☆19,066Updated this week
- Efficient Triton Kernels for LLM Training☆6,568Updated this week
- Fully open reproduction of DeepSeek-R1☆26,433Apr 2, 2026Updated 4 months ago
- UNet diffusion model in pure CUDA☆664Jun 28, 2024Updated 2 years ago
- Simple RL training for reasoning☆3,870Dec 23, 2025Updated 7 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,854May 11, 2025Updated last year
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆153Nov 11, 2024Updated last year
- Frontier Models playing the board game Diplomacy.☆694Jun 1, 2026Updated 2 months ago
- Democratizing Reinforcement Learning for LLMs☆5,785Updated this week
- 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.
- The best ChatGPT that $100 can buy.☆57,167Aug 2, 2026Updated last week
- slime is an LLM post-training framework for RL Scaling.☆7,885Updated this week
- gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI☆20,306Jul 24, 2026Updated 2 weeks ago
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,467May 7, 2026Updated 3 months ago
- LLM training in simple, raw C/CUDA☆30,789Jun 26, 2025Updated last year
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆5,113Jul 30, 2026Updated 2 weeks ago
- Implementation of Diffusion Transformer (DiT) in JAX☆322Jun 11, 2024Updated 2 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆62,082Nov 12, 2025Updated 9 months ago
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,676Jul 1, 2024Updated 2 years ago
- 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.
- Fast and memory-efficient exact attention☆24,701Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,554Updated this week
- Muon is an optimizer for hidden layers in neural networks☆2,779May 24, 2026Updated 2 months ago
- LLM101n: Let's build a Storyteller☆37,504Aug 1, 2024Updated 2 years ago
- Official PyTorch implementation for "Large Language Diffusion Models"☆3,936Jul 15, 2026Updated 3 weeks ago
- Minimalistic large language model 3D-parallelism training☆2,783May 26, 2026Updated 2 months ago
- Nano vLLM☆14,996Apr 26, 2026Updated 3 months ago