Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
☆2,969Sep 22, 2026Updated this week
Alternatives and similar repositories for miles
Users that are interested in miles are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- slime is an LLM post-training framework for RL Scaling.☆8,521Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,339Updated this week
- My learning notes for ML SYS.☆7,383Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,132May 17, 2026Updated 4 months ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,786Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- FlashInfer: Kernel Library for LLM Serving☆6,482Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,323Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,005Sep 15, 2026Updated last week
- Scalable toolkit for efficient model reinforcement☆2,027Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,566Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,184Updated this week
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,402Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆768Aug 29, 2026Updated 3 weeks ago
- Distributed Compiler and Optimized Parallel Kernels☆1,549Updated 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.
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,464Updated this week
- Agentic RL Training at Scale☆2,068Updated this week
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆625Updated this week
- TokenSpeed is a speed-of-light LLM inference engine.☆2,159Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,638Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,832Sep 12, 2026Updated last week
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆679Mar 21, 2026Updated 6 months ago
- 🚀 Efficient implementations for emerging model architectures☆5,782Updated this week
- An LLM post-training framework with vLLM for RL Scaling☆473Updated 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.
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,222Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,034Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,793Aug 13, 2026Updated last month
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,258Updated this week
- Allow torch tensor memory to be released and resumed later☆275Updated this week
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆926Updated this week
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆308Nov 7, 2025Updated 10 months ago
- An agentic-first and HuggingFace-native RL framework for research (9k lines).☆1,149Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆8,145Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- JAX backend for SGL☆353Updated this week
- Perplexity GPU Kernels☆608Nov 7, 2025Updated 10 months ago
- Building the Virtuous Cycle for AI-driven LLM Systems☆282May 1, 2026Updated 4 months ago
- ☆1,312May 20, 2026Updated 4 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆232Jun 15, 2026Updated 3 months ago
- Compact and Agent-Native MoE Training System☆353Updated this week
- Materials for learning SGLang☆894Jan 5, 2026Updated 8 months ago