get-beam VS runhouse

You should checkout https://beam.cloud (I'm the founder), it'll give you access to plenty of cloud GPU resources for training or inference.

Right now it's pretty hard to get GPU quota on AWS/GCP, so hopefully this is useful for you.

Cloudflare AI and Replicate are great for running off-the-shelf models, but anything custom is going to incur a 10+ minute cold start.

For running custom fine-tuned models on serverless, you could look into https://beam.cloud which is optimized for serving custom models with extremely fast cold start (I'm a little biased since I work there, but the numbers don't lie)

Serverless only works if the cold boot is fast. For context, my company runs a serverless cloud GPU product called https://beam.cloud, which we've optimized for fast cold start. We see Whisper in production cold start in under 10s (across model sizes). A lot of our users are running semi-real time STT, and this seems to be working well for them.

I’m Eli, and my co-founder and I built Beam to run workloads on serverless cloud GPUs with hot reloading, autoscaling, and (of course) fast cold start. You don’t need Docker or AWS to use it, and everyone who signs up gets 10 hours of free GPU credit to try it out.

Github with example apps and tutorials: https://github.com/slai-labs/get-beam/tree/main/examples

In this blog post, I want to make it as simple as possible to fine-tune the LLaMA 2 - 7B model, using as little code as possible. We will be using the Alpaca Lora Training script, which automates the process of fine-tuning the model and for GPU we will be using Beam.

With Runhouse, it’s easy to send code to your compute no matter where it lives, and efficiently utilize your resources across multiple callers scheduling jobs (e.g. researchers, pipelines, inference services, etc). We believe less is more when it comes to AI DevOps, so we don’t make any assumptions about the structure of your code or the infrastructure to which you’re sending it.

You may want to look at run.house [0] for a pretty powerful solution to many of these problems.

[0] https://github.com/run-house/runhouse

I was the product lead for PyTorch and was seeing the same problem all over, so I've been working on a new tool for exactly this: https://github.com/run-house/runhouse

I've been working on a very flexible and low-lift OSS ML platform that sounds like it would suit your needs: https://github.com/run-house/runhouse