AI Dynamics

Global AI News Aggregator

About

Jamba-1.5 Hybrid Architecture Delivers Superior Throughput and Latency Performance

The hybrid Jamba architecture enables Jamba-1.5 models to reach excellent throughput and latency, especially at long contexts. With the same hardware, Jamba-1.5 models are the fastest across the board (in the image: 2xA100 80GB GPUs for Mini, 8xA100 80GB GPUs for Large). 2/7

→ View original post on X — @ai21labs