Juice Labs

That's really awesome. I'm not sure what I'd use it for but just being able to makes me want to find an excuse! What's impressive is this seems to have more capabilities than…

Neato, sounds like bitfusion in their early days! Definitely of interest to us, even w/ latency limits, both for ai dev & investigations and occasional full runs I do have to…

I'm confused, where is the actual source code? This repo only has some Dockerfiles that, as far as I can tell, are pulling precompiled opaque binaries and have some convenience…

I don't think it's opensource. I assume it cost quite some $$$ to produce this because you kinda have to cut nvidias binary drivers in half, which is going to require quite a lot…

wait is the code actually FOSS or is this just freeware. I only see docker files.

It surprises me that this works well enough to be useful. I would have thought that network latency, being orders of magnitude higher than memory latency, would be a huge…

I'd be surprised if this works for anything latency sensitive over anything more than a LAN. Even just the time it takes speed of light between NY and LA (410^6m/310^8m/s=1/75s)…

no point without rdma enabled gpus…

For anything involving inference you’re much better off with one of the many inference model servers such as TensorFlow serving, Triton Inference Server, etc.

That's the biggest problem with this model. With inference it's better to just use a dedicated model server. For training it's better to deploy on a massive dedicated machine.…

I'm at the server limit and can't join additional servers without leaving something else. Can you add this stuff to the github repo?

Serverless GPU is all of the rage in the past month - I'd love to see a review of this from someone who knows how to benchmark a GPU workload. In particular: - Autoscaling Stable…

> *Basically, we aren't targeting support for graphical applications running on Linux because there is very little demand for this - but we cover everything else. You CAN run…

I doubt this does multi-server. All the GPUs probably have to be on the same machine.

I see lots of comments in various ML repositores about trouble running on multiple GPUs. This seems like a great way to run across multiple low VRAM GPUs instead of buying a huge…

CUDA Driver API or Runtime API remoting?

Driver.

Can this be used to accelerate video decode in a linux machine/virtual machine? It sounds like it is not for graphics on linux but it unclear to me where decode falls.

Would this allow a VMware Workstation Linux VM use the GPU from a Windows Host with an Nvidia Video Card for ML usage?

Didn't we have those things already? Virtual-GL and Co. say hi. Also for most real GPU applications, you need to get the data in and out. I don't think splitting compute across a…

Neato, sounds like bitfusion in their early days! Definitely of interest to us, even w/ latency limits, both for ai dev & investigations and occasional full runs I do have to…

For anything involving inference you’re much better off with one of the many inference model servers such as TensorFlow serving, Triton Inference Server, etc.

The datacenter is probably not thousands, but hundreds of kilometers away so there is room to deliver 60fps. I was surprised how well GeForce Now works.

Yeah, I've tried with shadow.tech and you can feel the latency. There's enough throughput to get a quality video stream through but there's enough latency to feel annoyed. I only…