Yet another tech startup wants to topple Nvidia with 'orders of magnitude' better energy efficiency; Sagence AI bets on analog in-memory compute to deliver 666K tokens/s on Llama2-70B

Sagence brings analog in-memory compute to redefine AI inferenceTen times lower power and 20 times lower costsAlso offers integration with PyTorch and TensorFlow Sagence AI has introduced an advanced analog…

Continue Reading Yet another tech startup wants to topple Nvidia with 'orders of magnitude' better energy efficiency; Sagence AI bets on analog in-memory compute to deliver 666K tokens/s on Llama2-70B