On-device VLM goes production: GenieX runs Liquid AI's LFM-VL live at PyTorch Conference
PyTorch · x · 2026-10-26
PyTorch amplified Alan (@alanzhuly)'s two demos at PyTorch Conference, in partnership with Qualcomm:
- On-device multimodal with GenieX: their open-source Gen AI runtime ran Liquid AI's LFM-VL on Innodisk's Dragonwing IQ9, watching a live camera feed and describing what it saw — entirely on device. His take: multimodal is the workload moving on-device in production; small VLMs are good enough now, with no per-frame cost or network latency
- Hands-on workshop with AWS: fine-tune on SageMaker, then run locally with GenieX. Most questions boiled down to "how do I get my own model on my own hardware?" — sovereign AI at the developer level
More from Embodied
- OmniEgoCap Turns Any Egocentric Device into a Full-Body 3D Mocap System — Scobleizer · 2026-10-26
- Tesla FSD approved in Latvia, the 10th European country — mitchdeg · 2026-10-26
- One long Claude Code session builds a full Android TV launcher with a 1-second-latency live camera — aristofeles · 2026-10-26
- LeCun co-authored Temporal Straightening: straightening latent paths boosts gradient-based planning success rates — ylecun · 2026-10-26
- Humanoid robots' DRAM demand may 20x, but it's still just 0.04% of 2026 supply — zephyr_z9 · 2026-10-26
- Microduck team publishes deep dives: relocalizes within 2cm using a 64-pixel depth sensor — mishig25 · 2026-10-26