Liquid AI הוציאה LFM2.5-VL-3B-DSpark: דיקוד ספקולטיבי למודלי תצלום-לשון עם עד 3.13x דיקוד מהיר יותר

תקציר מקורי באנגליתLiquid 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 are live on Hugging Face in Safetensors and GGUF , with day-one support in SGLang, MLX-VLM, and llama.cpp. Liquid AI team labels the release experimental, and it ships under the LFM Open License v1.0 , which allows free commercial use only for companies under $10M in annual revenue. What Speculative Decoding Changes for a VLM A standard model generates one token per forward pass. Speculative decoding adds a small draft