Cloudflare Enhances AI Inference Platform with Powerful GPU Upgrade, Faster Inference, Larger Models, Observability, and Upgraded Vector Database
Workers AI is the easiest place to build and scale AI applications; can now deploy larger models and handle more complex AI tasks
As large language models (LLMs) become smaller and more performant, network speeds will become the bottleneck to customer adoption and seamless AI interactions. Cloudflare’s globally distributed network helps to minimize network latency, setting it apart from other networks that are typically made up of concentrated resources in limited data centers. Cloudflare’s serverless inference platform, Workers AI, now has GPUs in more than 180 cities around the world, built for global accessibility to provide low latency times for end users all over the world. With this network of GPUs, Workers AI has one of the largest global footprints of any AI platform, and has been designed to run AI inference locally as close to the user as possible and help keep customer data closer to home.
“As AI took off last year, no one was thinking about network speeds as a reason for AI latency, because it was still a novel, experimental interaction. But as we get closer to AI becoming a part of our daily lives, the network, and milliseconds, will matter,” said
-
Upgraded performance and support for larger models: Now,
Cloudflare is enhancing their global network with more powerful GPUs for Workers AI to upgrade AI inference performance and run inference on significantly larger models like Llama 3.1 70B, as well as the collection of Llama 3.2 models with 1B, 3B, 11B (and 90B soon). By supporting larger models, faster response times, and larger context windows, AI applications built on Cloudflare’s Workers AI can handle more complex tasks with greater efficiency – thus creating natural, seamless end-user experiences. - Improved monitoring and optimizing of AI usage with persistent logs: New persistent logs in AI Gateway, available in open beta, allow developers to store users’ prompts and model responses for extended periods to better analyze and understand how their application performs. With persistent logs, developers can gain more detailed insights from users’ experiences, including cost and duration of requests, to help refine their application. Over two billion requests have traveled through AI Gateway since launch last year.
-
Faster and more affordable queries: Vector databases make it easier for models to remember previous inputs, allowing machine learning to be used to power search, recommendations, and text generation use-cases. Cloudflare’s vector database, Vectorize, is now generally available, and as of
August 2024 now supports indexes of up to five million vectors each, up from 200,000 previously. Median query latency is now down to 31 milliseconds (ms), compared to 549 ms. These improvements allow AI applications to find relevant information quickly with less data processing, which also means more affordable AI applications.
To learn more, please check out the resources below:
- Blog: Cloudflare’s Bigger, Better, Faster AI platform
- Blog: Making Workers AI faster and more efficient: Performance optimization with KV cache compression and speculative decoding
-
Join us online for demos, product announcements, and more at our first Builder
Day Live Stream today,September 26 at11am PT . Register at https://builderday.pages.dev.
About
Powered by one of the world’s largest and most interconnected networks,
Learn more about Cloudflare’s connectivity cloud at cloudflare.com/connectivity-cloud. Learn more about the latest Internet trends and insights at https://radar.cloudflare.com.
Follow us: Blog | X | LinkedIn | Facebook | Instagram
Forward-Looking Statements
This press release contains forward-looking statements within the meaning of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934, as amended, which statements involve substantial risks and uncertainties. In some cases, you can identify forward-looking statements because they contain words such as “may,” “will,” “should,” “expect,” “explore,” “plan,” “anticipate,” “could,” “intend,” “target,” “project,” “contemplate,” “believe,” “estimate,” “predict,” “potential,” or “continue,” or the negative of these words, or other similar terms or expressions that concern Cloudflare’s expectations, strategy, plans, or intentions. However, not all forward-looking statements contain these identifying words. Forward-looking statements expressed or implied in this press release include, but are not limited to, statements regarding the capabilities and effectiveness of Workers AI, AI Gateway, Vectorize, R2,and Cloudflare’s other products and technology, the benefits to Cloudflare’s customers from using Workers AI, AI Gateway, Vectorize, R2, and Cloudflare’s other products and technology, the timing of when Workers AI, AI Gateway, Vectorize, R2, or any of its related features will be generally available to all current and potential
The forward-looking statements made in this press release relate only to events as of the date on which the statements are made.
© 2024
View source version on businesswire.com: https://www.businesswire.com/news/home/20240926193441/en/
Vice President, Head of
press@cloudflare.com
Source: