I did my share of OCR funny business by running the Firebase OCR SDK inside an android app acting as a webserver, through nested virtualization back in 2018. Nothing at that time beat it's accuracy & throughput for something which ran offline once the weights were fetched into the container.
Looking forward to GPU support for workers. Cloudflare announced they were working on it in 2021 [1], but it doesn't seem generally available yet; they still have a signup page for notification [2].<p>I know other companies have struggled with demand, so maybe they're doing it on an invite basis.<p>[1]: <a href="https://blog.cloudflare.com/workers-ai/" rel="nofollow noreferrer">https://blog.cloudflare.com/workers-ai/</a>
[2]: <a href="https://www.cloudflare.com/nvidia-workers/" rel="nofollow noreferrer">https://www.cloudflare.com/nvidia-workers/</a>
I don't get it, how is this useful?<p>- Takes 1.5 seconds to run, so there goes the "edge" benefit.<p>- And if it takes that long, it would cost more than having it running on a proper instance/vps.
Why are Cloudflare Workers limited to languages that compile to Wasm? Can't they use a container of some sort to isolate the code? Many languages can be compiled to Wasm but many times is quirky.
The "Why Edge Compute?" section compares running OCR on a Cloudflare Worker against on-device but the first two advantages also apply to running on-device (low latency and low cost). Is this a mistake in the article or do I not understand correctly?
The beta link is broken: <a href="https://www.cloudflare.com/constellation/" rel="nofollow noreferrer">https://www.cloudflare.com/constellation/</a>
I use the word Edge and Microservice in my head interchangeably. If something does not make sense for a microservice, then it does not make sense for the Edge.