DeepSeek DSpark promette un'AI più veloce e meno costosa grazie a una nuova ottimizzazione dell'inferenza, senza creare un nuovo modello.

DeepSeek's new DSpark framework delivers 60% to 85% faster inference speeds for its V4 models through speculative decoding, with throughput gains up to

Start-up unveils speculative decoding framework that speeds up inference by up to 85 per cent amid China’s push to overcome US AI curbs.