X · @nvidia
· X / Twitter
NVIDIA inference software keeps driving down token costs, long after AI infrastructure is deployed. ⚡ In just one month on NVIDIA Blackwell, software…
NVIDIA inference software keeps driving down token costs, long after AI infrastructure is deployed. ⚡In just one month on NVIDIA Blackwell, software optimizations improved DeepSeek V4 performance by up to 5×, reducing token costs to roughly one-fifth of previous levels. NVIDIA's integrated inference software stack comp