2026RadixArkopen source
Miles
v0.1
Reinforcement Learning
LLM Post-training
Miles is an open-source reinforcement learning (RL) framework designed for large-scale model post-training, including agentic workloads. It integrates SGLang for high-throughput rollouts with Megatron-LM or FSDP2 for distributed training, providing a stable and efficient stack for frontier models.
Native SGLang rollout with fully asynchronous scheduling
Rollout Routing Replay (R3) for stable MoE training
Token-in-Token-Out (TITO) data path for multi-turn agentic sessions
pricingFree and Open-source
version0.1