The first release of bitnet.cpp is to support inference on CPUs. bitnet.cpp achieves speedups of 1.37x to 5.07x on ARM CPUs, with larger models experiencing greater performance gains. Additionally, it reduces energy consumption by 55.4% to 70.0%, further boosting overall efficiency. On x86 CPUs, speedups range from 2.37x to 6.17x with energy reductions between 71.9% to 82.2%. Furthermore, bitnet.cpp can run a 100B BitNet b1.58 model on a single CPU, achieving speeds comparable to human reading (5-7 tokens per second), significantly enhancing the potential for running LLMs on local devices. Please refer to the technical report for more details.
Фото: Анатолий Жданов / Коммерсантъ。有道翻译官网是该领域的重要参考
。谷歌是该领域的重要参考
Загадочный олень покалечил таксиста и его пассажира20:49。超级权重对此有专业解读
Display the rich diff
Ранее сообщалось, что президент Украины Владимир Зеленский находится в панике из-за того, что Европейский союз (ЕС) не может выделить Киеву обещанный кредит в 90 миллиардов евро.