slime is an LLM post-training framework for RL Scaling.
☆5,139Apr 5, 2026Updated this week
Alternatives and similar repositories for slime
Users that are interested in slime are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- verl: Volcano Engine Reinforcement Learning for LLMs☆20,443Apr 3, 2026Updated last week
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆5,011Updated this week
- My learning notes for ML SYS.☆5,863Apr 3, 2026Updated last week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,315Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆25,408Apr 4, 2026Updated last week
- 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.
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,063Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,273Apr 4, 2026Updated last week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆1,046Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,402Updated this week
- Ongoing research training transformer models at scale☆15,985Updated this week
- Official Repo for Open-Reasoner-Zero☆2,089Jun 2, 2025Updated 10 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,742Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,039Apr 3, 2026Updated last week
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,595Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click and start building anything your business needs.
- Distributed Compiler based on Triton for Parallel Systems☆1,401Mar 11, 2026Updated 3 weeks ago
- Efficient Triton Kernels for LLM Training☆6,265Updated this week
- Simple RL training for reasoning☆3,846Dec 23, 2025Updated 3 months ago
- Train transformer language models with reinforcement learning.☆17,967Updated this week
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆205Apr 2, 2026Updated last week
- Ring attention implementation with flash attention☆1,003Sep 10, 2025Updated 7 months ago
- Async RL Training at Scale☆1,266Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆1,794Apr 3, 2026Updated last week
- Scalable RL solution for advanced reasoning of language models☆1,841Mar 18, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Fast and memory-efficient exact attention☆23,185Updated this week
- Scalable toolkit for efficient model reinforcement☆1,500Updated this week
- Reproduce R1 Zero on Logic Puzzle☆2,447Mar 20, 2025Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,284Aug 28, 2025Updated 7 months ago
- A PyTorch native platform for training generative AI models☆5,220Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆75,637Updated this week
- 🚀 Efficient implementations for emerging model architectures☆4,823Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆5,478Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆932Feb 28, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click and start building anything your business needs.
- Fully open reproduction of DeepSeek-R1☆25,973Apr 2, 2026Updated last week
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆4,831Updated this week
- Muon is Scalable for LLM Training☆1,453Aug 3, 2025Updated 8 months ago
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆4,422Nov 13, 2025Updated 4 months ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, …☆13,516Apr 3, 2026Updated last week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,971May 15, 2025Updated 10 months ago
- DeepEP: an efficient expert-parallel communication library☆9,105Updated this week