IFM open-sources RL360, the agentic RL infra behind K2 Horizon's training
rupspace · x · 2026-10-23
The IFM team released RL360, the agentic RL training infrastructure used to train the K2 Horizon series (375B total / 23B active params), built on radixark's miles with extensive optimizations for efficient agentic RL at scale. Per Artificial Analysis, K2 Horizon 375B A23B scores 31 on the Intelligence Index (median 19), runs at 1067 output tokens/s (rank 1), has a 524k context window, and ships under Apache 2.0.
Related event: IFM Open-Sources RL360, Massive Agentic RL Infrastructure Behind K2 Horizon(2 posts)→
More from Infra
- Investor Ron Baron claims SpaceX books $25B a year selling compute to Anthropic and Google — elonmusk · 2026-10-23
- Open-source Phosphene renders Hailuo H3 2.3x faster locally on Mac — cocktailpeanut · 2026-10-23
- Modal raises $750M at $15.75B as inference booms; 20VC probes AI valuation cracks — sarahcat21 · 2026-10-23
- Cadence announces sovereign AI cloud for European chip designers — karlfreund · 2026-10-23
- SGLang Deep-Dive Blog Series Breaks Down KV Cache, Posts up to 15.5x Throughput Gains — BanghuaZ · 2026-10-23
- DynaLM: Open-Source CPU-First LLM Inference Engine Seeks Feedback — Unlikely_Safety_7456 · 2026-10-23