Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,898Apr 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.☆1,703Nov 21, 2025Updated 9 months ago
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆5,008Oct 27, 2025Updated 10 months ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,295Aug 26, 2025Updated last year
- 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 10 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- NanoGPT (124M) in 90 seconds☆5,735Aug 9, 2026Updated 3 weeks ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆629Oct 7, 2025Updated 10 months ago
- Minimal reproduction of DeepSeek R1-Zero☆13,227Feb 27, 2026Updated 6 months ago
- Our library for RL environments + evals☆4,581Updated 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☆5,692Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,258Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,969Aug 13, 2026Updated 3 weeks ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,275Aug 27, 2025Updated last year
- 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.
- Train transformer language models with reinforcement learning.☆19,198Updated this week
- Efficient Triton Kernels for LLM Training☆6,597Updated this week
- Fully open reproduction of DeepSeek-R1☆26,450Apr 2, 2026Updated 5 months ago
- UNet diffusion model in pure CUDA☆663Jun 28, 2024Updated 2 years ago
- Simple RL training for reasoning☆3,874Dec 23, 2025Updated 8 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,863May 11, 2025Updated last year
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆152Nov 11, 2024Updated last year
- Democratizing Reinforcement Learning for LLMs☆5,813Aug 24, 2026Updated last week
- The best ChatGPT that $100 can buy.☆57,738Aug 2, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- slime is an LLM post-training framework for RL Scaling.☆8,354Updated this week
- gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI☆20,361Jul 24, 2026Updated last month
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,510May 7, 2026Updated 3 months ago
- LLM training in simple, raw C/CUDA☆30,914Jun 26, 2025Updated last year
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆5,141Updated this week
- Implementation of Diffusion Transformer (DiT) in JAX☆321Jun 11, 2024Updated 2 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆62,737Nov 12, 2025Updated 9 months ago
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,702Jul 1, 2024Updated 2 years ago
- Fast and memory-efficient exact attention☆24,833Updated this week
- 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.
- 🚀 Efficient implementations for emerging model architectures☆5,682Updated this week
- Muon is an optimizer for hidden layers in neural networks☆2,816May 24, 2026Updated 3 months ago
- LLM101n: Let's build a Storyteller☆37,503Aug 1, 2024Updated 2 years ago
- Official PyTorch implementation for "Large Language Diffusion Models"☆3,954Jul 15, 2026Updated last month
- Minimalistic large language model 3D-parallelism training☆2,806May 26, 2026Updated 3 months ago
- Nano vLLM☆15,282Apr 26, 2026Updated 4 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆90,787Updated this week