Miles v0.1 launches: open-source RL framework with 1,326 commits, 85 GPU CI tests
ying11231 · x · 2026-08-19
The team behind Miles released v0.1, an open-source RL training framework for LLMs and multimodal models, aiming to make large-scale RL correct, efficient, and debuggable.
- 72 contributors landed 1,326 commits over 9 months, with 85 GPU end-to-end CI tests.
- Battle-tested on frontier open models like Kimi K3, DeepSeek V4, Qwen 3.8, GLM 5.2, and MiniMax H3.
- Uses SGLang as the native rollout engine, paired with Megatron-LM and FSDP for training; supports both LLMs and diffusion models.
- Powers production RL at humansand, periodiclabs, Modal, Decagon, Nebius, IBM and more, on both NVIDIA and AMD hardware.
Related event: RadixArk open-sources Miles v0.1, an RL training framework for LLMs(9 posts)→
More from coding & agent
- Six-month prediction: hiring for generic agent harnesses built from scratch will cool — yi111 · 2026-10-16
- Omarchy ISO wouldn't boot on NVIDIA, so he had Claude patch it — indragie · 2026-10-16
- Dev uses Grok to clean up 3D printer firmware, catches it sneaking in nonsense code — yacineMTB · 2026-10-16
- A rude AI agent took 89% of a shared resource in 102-run multi-agent personality experiment — Brave-History-6502 · 2026-10-16
- Guardrails can make risky delegation work — but it takes a full-time team, says iandanforth — iandanforth · 2026-10-16
- What can you truly delegate? Only tasks with unambiguous, verifiable results — iandanforth · 2026-10-16