Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,911Apr 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.☆1,718Nov 21, 2025Updated 11 months ago
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆5,065Oct 27, 2025Updated last year
- Simple MPI implementation for prototyping or learning☆332Aug 6, 2025Updated last year
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,336Aug 26, 2025Updated last year
- Minimal reproduction of DeepSeek R1-Zero☆13,255Feb 27, 2026Updated 8 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.
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆363Nov 2, 2025Updated last year
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆640Oct 7, 2025Updated last year
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,604Jan 12, 2025Updated last year
- NanoGPT (124M) in 90 seconds☆6,001Sep 28, 2026Updated last month
- Our library for RL environments + evals☆4,760Updated this week
- A PyTorch native platform for training generative AI models☆5,868Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,091Updated this week
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,286Aug 27, 2025Updated last year
- Efficient Triton Kernels for LLM Training☆6,679Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆156Nov 11, 2024Updated last year
- Implementation of Diffusion Transformer (DiT) in JAX☆322Jun 11, 2024Updated 2 years ago
- Train transformer language models with reinforcement learning.☆19,649Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,134Oct 5, 2026Updated 3 weeks ago
- UNet diffusion model in pure CUDA☆669Jun 28, 2024Updated 2 years ago
- Fully open reproduction of DeepSeek-R1☆26,475Oct 26, 2026Updated last week
- Simple RL training for reasoning☆3,880Dec 23, 2025Updated 10 months ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆979Nov 16, 2025Updated 11 months ago
- Frontier Models playing the board game Diplomacy.☆710Jun 1, 2026Updated 5 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,956May 11, 2025Updated last year
- LLM training in simple, raw C/CUDA☆31,354Jun 26, 2025Updated last year
- Fast and memory-efficient exact attention☆25,235Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,905Oct 16, 2026Updated 2 weeks ago
- gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI☆20,508Updated this week
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,976Jul 1, 2024Updated 2 years ago
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,571May 7, 2026Updated 5 months ago
- The best ChatGPT that $100 can buy.☆59,348Sep 7, 2026Updated last month
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆5,209Sep 19, 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.
- slime is an LLM training framework for RL Scaling.☆8,774Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,267Aug 22, 2025Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆64,323Nov 12, 2025Updated 11 months ago
- LLM101n: Let's build a Storyteller☆37,473Aug 1, 2024Updated 2 years ago
- Muon is an optimizer for hidden layers in neural networks☆2,919May 24, 2026Updated 5 months ago
- Schedule-Free Optimization in PyTorch☆2,333Jul 28, 2026Updated 3 months ago
- Fast bare-bones BPE for modern tokenizer training☆180Jun 23, 2025Updated last year