Accelerating vision-language models with LFM2.5-VL-DSpark
Accelerating vision-language models with LFM2.5-VL-DSpark Faster inference: decode speedups up to 3.13x on device and 2.66x on an H100, with end-to-end gains up to 2.62x and 2.27x. Small memory cost: the drafter adds 280M parameters, 8.9%...
Read more: https://huggingface.co/blog/LiquidAI/lfm2-5-vl-dsp...
Scan with your phone
Scan with your phone