Open-Source RL Framework Miles Debuts for Enterprise LLM and VLM Post-Training
AravSrinivas · x · 2026-09-03
- Perplexity CEO Arav Srinivas shares Miles, an open-source "RL-as-a-service" framework for enterprise LLM/VLM post-training, forked from and co-evolving with slime; 2.3k GitHub stars.
- Miles v0.1 is out, positioned as production-level post-training.
- Highlights: Blackwell-native 8-bit/4-bit RL with end-to-end MXFP8 and NVFP4 support; day-0 Kimi K3 support alongside SGLang.
More from Infra
- FastVideo-FastH3 appears on MLX listing ahead of actual model release — Structure-These · 2026-09-03
- South Korean exports jump 69% YoY in August on AI hardware demand — VraserX · 2026-09-03
- RTX 5090 writes nightly stock briefs with a numbers gate so the LLM can't invent figures — JakeChj · 2026-09-03
- CXMT reaches 10% global DRAM market share in Q2, Counterpoint Research says — zephyr_z9 · 2026-09-03
- You Don't Run a Model, You Run Kernels: Why Inference Performance Hides in Fused Kernels — EAccelerate_42 · 2026-09-03
- KAIST's Declarative Attention lets LLMs skip most KV cache reads — kaist-ai · 2026-09-03