InfoWorld

Google targets AI inference bottlenecks with TurboQuant

The technique aims to ease GPU memory constraints that limit how enterprises scale AI inference and long-context applications ...

Nvidia says it can shrink LLM memory 20x without changing model weights

Nvidia's KV Cache Transform Coding (KVTC) compresses LLM key-value cache by 20x without model changes, cutting GPU memory ...
Semiconductor Engineering

Memory Wall Problem Grows With LLMs

The growing imbalance between the amount of data that needs to be processed to train large language models (LLMs) and the inability to move that data back and forth fast enough between memories and ...
TweakTown

Meta's huge 16,384 NVIDIA H100 AI GPU cluster: HBM3 memory crashed half of Llama 3 training

Meta released a new study detailing its Llama 3 405B model training, which took 54 days with the 16,384 NVIDIA H100 AI GPU cluster. During that time, 419 unexpected component failures occurred, with ...

Meet the Kioxia GP Series SSD designed to expand GPU memory and tackle trillion-parameter AI models

Meet the Kioxia GP Series SSD designed to expand GPU memory and tackle trillion-parameter AI models ...