Armory: Serve large robot policies to 10+ robots on a single GPU, boosting throughput by 18%
danfei_xu · x · 2026-08-03
Stanford researchers introduce Armory, a system for serving large robot policies (VLA/WAM) from cloud/edge. By real-time scheduling of action chunks, Armory enables a single GPU to serve 10+ robots simultaneously without pausing. On heterogeneous fleets, it boosts task throughput by up to 18% over baselines. The work frames policy serving as a scheduling problem with real-time constraints, where robot waiting for inference can cause failures.
More from Embodied
- Jensen Huang: Video Generation Models Have Solved the Physics Intuition for Robotics — r0ck3t23 · 2026-08-03
- OpenAI Hardware Roadmap Leaks: $200 Screenless Speaker and AI Phone Target 2027 — 创业邦 · 2026-08-03
- ACE-Data-0: New Embodied Data Engine on Hugging Face with 150 Hours of Multimodal Data — liuziwei7 · 2026-08-03
- Applying LLM Sampling Params to Robots: Low Temperature Causes Hilarious Fails — carlosdponx · 2026-08-03
- FCC Ban Fallout: US Humanoid Robot Orders Surge Amid Global Collaboration Concerns — chris_j_paxton · 2026-08-03
- Insight: Humanoid Hardware is Converging; Data Pipelines Are the Real Moat — chris_j_paxton · 2026-08-03