Infinigence open-sources APXInf: cuts embodied AI on-robot inference latency from 278ms to 26ms
青稞AI · wechat · 2026-09-15
Infinigence (Wuxin Qiong), with Tsinghua and Shanghai Jiao Tong University, open-sourced APXInf, an edge inference engine designed for deploying embodied AI models on real robots.
- Performance: end-to-end inference latency for π0.5 FP8 on Jetson Thor cut from 278ms to under 26ms (38.46Hz), enabling real-time robot control
- Stability: minimal Rust runtime with Python interface, memory-safe by design for long-running deployment
- Agility: built for Agentic Engineering — an agent system automatically explores and optimizes kernels, simplifying new model onboarding
First release supports π0.5 and WALL-OSS on Jetson Orin/Thor and RTX 4090. APXInf joins the RLinf ecosystem to bridge training and on-robot deployment; roadmap includes Qwen, Groot, nvfp4 optimization, and domestic chip support.
More from Embodied
- Four Growers robots harvest in real time using stereo cameras and vacuum nozzles — anselm · 2026-09-15
- Figure Humanoid Steps Out of a Self-Driving Car and Keeps Walking, Sparking 'Last Mile' Talk — xmercury_one · 2026-09-15
- Agility confirms Digit v5 launching Q3, teases wheeled variant — CyberRobooo · 2026-09-15
- Zurich-Munich is the West's densest robotics talent hub, investor says — arian_ghashghai · 2026-09-15
- Robot Data Startup Mecka AI Nears Sequoia-Led Round at ~$500M Valuation — 快鲤鱼 · 2026-09-15
- Agility unveils Digit 5, a humanoid built to work beside people without barriers — XxSpookxX · 2026-09-15