Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
☆2,306Sep 2, 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.☆8,354Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,228Updated this week
- My learning notes for ML SYS.☆7,160Aug 19, 2026Updated 2 weeks ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,935May 17, 2026Updated 3 months ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,712Updated this week
- 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.
- FlashInfer: Kernel Library for LLM Serving☆6,318Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆33,326Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,004Aug 12, 2026Updated 3 weeks ago
- Scalable toolkit for efficient model reinforcement☆1,974Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,258Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,144Updated this week
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,380Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆753Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,530Aug 12, 2026Updated 3 weeks ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆584Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,328Updated this week
- Agentic RL Training at Scale☆2,008Updated this week
- TokenSpeed is a speed-of-light LLM inference engine.☆2,075Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,468Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,813Aug 24, 2026Updated last week
- An LLM post-training framework with vLLM for RL Scaling☆447Updated this week
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆677Mar 21, 2026Updated 5 months ago
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,063Updated this 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.
- 🚀 Efficient implementations for emerging model architectures☆5,682Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,747Aug 13, 2026Updated 2 weeks ago
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,186Updated this week
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆896Updated this week
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆308Nov 7, 2025Updated 9 months ago
- 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 2 weeks ago
- Allow torch tensor memory to be released and resumed later☆273Aug 21, 2026Updated last week
- An agentic-first RL framework for research (9k lines).☆1,001Updated this week
- Perplexity GPU Kernels☆604Nov 7, 2025Updated 9 months ago
- 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.
- Compact and Agent-Native MoE Training System☆345Updated this week
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆231Jun 15, 2026Updated 2 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆7,950Updated this week
- JAX backend for SGL☆348Updated this week
- ☆1,310May 20, 2026Updated 3 months ago
- Materials for learning SGLang☆884Jan 5, 2026Updated 7 months ago
- Building the Virtuous Cycle for AI-driven LLM Systems☆277May 1, 2026Updated 4 months ago