Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for Vision-Language Models With Up to 3.13x Faster Decoding

Liquid AI has announced LFM2.5-VL-3B-DSpark, an experimental speculative-decoding draft model for its LFM2.5-VL-3B vision-language model. The drafter adds about 280M parameters and speeds up decoding without changing the model’s output. Liquid AI team reports up to 3.13x faster decoding on Apple silicon and up to 2.66x on an NVIDIA H100. Is it deployable? Yes, Weights…

Read Full News

Police, fire or ambulance? Winnipeg launching 4th option for 911 mental health calls – Winnipeg

The City of Winnipeg is taking the next steps on a fourth emergency response pathway, after the model was approved by city council. “Presently, when someone calls 911, the dispatcher only has three choices,” Mayor Scott Gillingham told Winnipeg city council Thursday. “They can send police officers, firefighters or paramedics — but not every call…

Read Full News