EdgeRock open-sourced: multimodal reasoning at constant memory with O(1) history for edge devices
xiaohu · x · 2026-10-23
xiaohu released EdgeRock, an open-source (Apache-2.0) project for "strong reasoning at constant memory": multimodal models with O(N) generation and O(1) persistent history, avoiding unbounded memory growth during long-context inference. It targets robots, unmanned vehicles and edge hardware where memory is fixed and shared with camera, radar and motor control. The repo (557 stars) ships inference and evaluation code, vLLM/SGLang integrations, a technical report, and weights on Hugging Face (rockmatrix-ai/EdgeRock).
Related event: EdgeRock Open-Sources Constant-Memory Multimodal Inference for Edge Devices(4 posts)→
More from Embodied
- Figure claims 81 min of robot data per second; critic calls it low-value slop — MarcJSchmidt · 2026-10-23
- FSD 14 lite driver review: near-perfect performance, HW3 is all you need — haydendevs · 2026-10-23
- First real-world sighting of a Tesla Cybercab on public roads — MatthewChang · 2026-10-23
- ETH Zurich's ACP teaches Unitree G1 whole-body ladder climbing with 13 minutes of demos — CyberRobooo · 2026-10-23
- NVIDIA GTC robotics roundup: Agile ONE SN humanoid, Isaac Lab 3.0, and Jensen's 'ChatGPT moment' — lukas_m_ziegler · 2026-10-23
- Tesla patent reveals flat-printing and thermoforming process for mass-producing robot fingertip touch sensors — CyberRobooo · 2026-10-23