Fastly, Inc. (FSLY) shares soared 5.1% in the pre-market session on Monday, following the company's announcement of the launch of its new product, Fastly AI Accelerator. This semantic caching solution aims to address the critical performance and cost challenges faced by developers with Large Language Model (LLM) generative AI applications like OpenAI's ChatGPT and Microsoft's Azure AI Foundry.
According to Fastly, the AI Accelerator can deliver an average of 9x faster response times for LLM applications by caching repeated queries, leading to enhanced performance, lower costs, and ultimately a better experience for developers. The solution can be easily implemented by just updating the application to a new API endpoint, typically requiring only a single line of code change.
Fastly's Chief Product Officer, Kip Compton, emphasized the importance of addressing the performance bottleneck faced by developers with LLM generative AI apps, stating, "With Fastly AI Accelerator we're already averaging 9x faster response times and we're just getting started. We want everyone to join us in the quest to make AI faster and more efficient."
Comments