#ai-inference

[ follow ]
#machine-learning
Artificial intelligence
fromInfoQ
1 week ago

Google Enhances LiteRT for Faster On-Device Inference

LiteRT simplifies on-device ML inference with enhanced GPU and NPU support for faster performance and lower power consumption.
Artificial intelligence
fromIT Pro
1 month ago

'TPUs just work': Why Google Cloud is betting big on its custom chips

Google's seventh generation TPU, 'Ironwood', aims to lead in AI workload efficiency and cost-effectiveness.
TPUs were developed with a cohesive hardware-software synergy, enhancing their utility for AI applications.
Artificial intelligence
fromInfoQ
1 week ago

Google Enhances LiteRT for Faster On-Device Inference

LiteRT simplifies on-device ML inference with enhanced GPU and NPU support for faster performance and lower power consumption.
Artificial intelligence
fromIT Pro
1 month ago

'TPUs just work': Why Google Cloud is betting big on its custom chips

Google's seventh generation TPU, 'Ironwood', aims to lead in AI workload efficiency and cost-effectiveness.
TPUs were developed with a cohesive hardware-software synergy, enhancing their utility for AI applications.
#nvidia
Silicon Valley
fromBusiness Insider
2 months ago

2 reasons why Nvidia's Jensen Huang isn't worried

Nvidia CEO Jensen Huang is confident in sustained demand for Nvidia chips due to new powerful GPUs and an industry shift towards AI inference.
Silicon Valley
fromBusiness Insider
2 months ago

2 reasons why Nvidia's Jensen Huang isn't worried

Nvidia CEO Jensen Huang is confident in sustained demand for Nvidia chips due to new powerful GPUs and an industry shift towards AI inference.
fromTheregister
7 months ago

Supermicro crams 18 GPUs into a 3U box

Supermicro's SYS-322GB-NR manages to fit 18 GPUs in just 3U rack space, catering to machine learning and AI inference workloads with low latency requirements.
Miscellaneous
[ Load more ]