Marconi Prefix Caching For The Era Of Hybrid Llms
2 mentions across 1 person
Visit ↗All mentions
“# Marconi: Prefix Caching for the Era of Hybrid LLMs _Blog post by Ravi Netravali_ https://arxiv.org/abs/2411.19379”
Marconi: Optimized Prefix Caching for Hybrid LLMs ↗“We present Marconi, the first system that supports efficient prefix caching with Hybrid LLMs.”
Marconi: Optimizing Prefix Caching for Hybrid LLMs ↗