Miles v0.2 Debuts at SGLang Summit: RL Training Across NVIDIA, AMD, TPU, Trainium
ying11231 · x · 2026-11-13
RadixArk launched Miles v0.2 at SGLang Summit, a production RL training framework broadening hardware and workload support:
- Hardware choice: NVIDIA and AMD GPUs, early Google TPU support, AWS Trainium coming soon
- Stable on messy fleets: mixed GPUs, mixed precisions, fully async rollouts
- Broader workloads: faster, lighter multimodal RL across image, video, and audio; async diffusion training; Multi-LoRA sharing one base model across jobs
More from Infra
- H100 rental fell from ~$8/hr in 2023 to ~$2.50 as decentralized training net SN44 keeps running — richdotca · 2026-11-13
- Unverified: Jensen Huang steps down as NVIDIA CEO; traders favor CUDA creator Ian Buck at 34% — morganlai · 2026-11-13
- Chinese major models reportedly trained on Blackwell-class chips, though scale disappoints — teortaxesTex · 2026-11-13
- Sentdex: 'China spy' claim is likely BS — more likely mutual export-restriction circumvention — Sentdex · 2026-11-13
- Analyst: DeepSeek V4's Flash variant is winning, and a hyper-efficient 2B V5 could be the real play — teortaxesTex · 2026-11-13
- vLLM ships recipe for Thinking Machines' Inkling-2-Small: 594B MoE, 1M context, ~1,100 tok/s/GPU — vllm_project · 2026-11-13