If you've been around Macs long enough this is very much in Apple's wheelhouse. They already do something similar with Final Cut Pro rendering, Logic Pro, Grand Central Dispatch, and XCode distributed CI/CD. Apple HQ is probably sitting on 1000s of nodes, high powered MBPs, iMacs, that could do lots of inference work overnight.
Minions is an internal enterprise system already in use at Apple. It pools idle Mac GPUs into a shared compute cluster for ML inference.
There is no distributed execution of a single LLM across multiple GPUs using tensor parallelism here. Instead, it relies on task-level parallelism-breaking down a large workload into independent subtasks that run across separate machines. For example, generating embeddings for a million documents.
I guess for companies this can be nice? Run some inference in the off-hours on the machines that you already have. Could be useful for analytical tasks that don't require to be instant. On the technical side this doesn't seem that groundbreaking for me though.
My warm take is that Apple is leaving a lot of money on the table by not investing in creating an independent supply chain for their chips and building their own cloud. They arguably had the first mover advantage when it came to general purpose arm compute; all they had to do was flood the market and make it easy for anyone to rent it. Not only would they corner a part of the market but perhaps ease demand pressure on other chip manufacturers too.
Apart from straight up buying TSMC's or Samsung's fabs I don't see a way of building a vertically integrated high-end chip supply chain for Apple. At least not on timeframes measured below a decade. And on those time frames the current supply issues will probably be resolved by companies who put all their effort into it instead of just tweaking their bottom line.
My guess is that they have challenges scaling the production anyway (6-16 weeks wait time for Studios), and also they would leave money in the table if they just released chips. I would assume that once they scale the production they will get back to the server game - MacOS server racks, or something more inventive like MacOS supercomputers running on a ton of prev gen chips ;)
They don't get enterprise, A/UX, mkLinux, OS X Server, Mac Pro tower, all gone now.
Swift's main reason to go open source and have good Linux support was naturally for app developers to be able to use it on server side, which naturally wasn't going to be macOS.
I macOS wasn't required for developing iDevices apps, they would surely sell even less desktops.
As with all similar SETI@home approaches, this paper does not address the energy cost.
Yes, we can distribute tasks to idle machines in homes and on office desktops, but it is often much more expensive than sending it to a data center where power is cheaper and the hardware is more efficient.
It would be so incredibly cool if we finally had an accessible consumer-accessible way to turn a network of computers on a network into a supercomputer. A household has a child who gets into 3D artwork and wants to render something? People can opt their tablets, phones, laptops, whatever to crunch out some frames overnight while not being used.
There is a startup working on this called Distributive I used to work for - their compute nodes are based on js/wasm runtimes so you just need a web browser to turn a device into a compute node...
until you get a teen obsessed with 3d rendering then they're up all night finding a way to convert manga into 3d scenes and your old laptop is running 100% cpu trying to keep up. xDD
The idealized version of this in my mind has a consent-first interface which makes it easy to set boundaries and limits and wouldn't burn out the machine as a default
That seems to be the point: you leverage existing workstations on your corporate network and run compute batches at night while they're idle. You don't have to buy any extra servers for your low-priority AI workloads.
We were doing this decades ago with engineer's HP C3600s under their desks. It wasn't AI, just low-priority HPC / fluid stuff batched out to hundreds of workstations.
That was the original pitch for Ian Murdock's Progeny startup in the late 90s: a Linux-based distributed filesystem for corporate desktops to boot into overnight for distributed computing.
Imagine if Apple made a GENERIC distributed compute framework to leverage idle computing power from Macs for distributed Rendering/Compiling/etc use cases. I'm sure Apple could convince Adobe and others to support this framework for their compute-intensive products and create a really interesting ecosystem for it.
Then universities and business could reduce their need for cloud and have a reason to put that spending towards higher end Macs...
I don't get it. In the paper it sounds like it's "just" a CRUD DB, then you have some fleet of Macs, and they store inputs and outputs in S3. What's the innovation here? Not trying to poo on this, but it looked like the most basic and obvious approach.
There are a lot of parallels between the DGX (and clones) series devices and these Apple devices, maybe it would be possible to rope in the DGX boxes as well. There's lots of them out there and I'm pretty sure not all of them have high utilization.
Would love to build something like this but for classification models that run on CPU. Like a “Classify @ Home” p2p compute network, to which people could contribute their machines and see what work is being done
It's not a novel idea, but its provable that someone can take this same concept and do something truly groundbreaking. I wonder if there's value in the idea that you can join a supercomputer network of MAC/Nvidia GPUs as a way of getting off cloud and into "our cloud". As long as you offer compute, you have credit into the system to be able to support your own workloads that can't be done on just your hardware. Need to address concerns about privacy, abuse, etc, but Apple's idea here has some merit if applied right.
Reading the “paper”, this is just a job runner built on Ollama.
Exo, and the teams at Apple that built the foundations Exo uses, actually use modern distributed compute.
Apple has released some small models previously that seemed genuinely great, along with some quality research/efforts. I’m just not seeing the same level of depth here, am I missing something?
If you've been around Macs long enough this is very much in Apple's wheelhouse. They already do something similar with Final Cut Pro rendering, Logic Pro, Grand Central Dispatch, and XCode distributed CI/CD. Apple HQ is probably sitting on 1000s of nodes, high powered MBPs, iMacs, that could do lots of inference work overnight.
[0] https://en.wikipedia.org/wiki/Grand_Central_Dispatch
[1] https://developer.apple.com/documentation/dispatch
Pardon me not understanding what this is about?
Basically SETI for AI workloads? At least, this is the impression the landingpage left me with.
I am a bit lost, tbh.
Minions is an internal enterprise system already in use at Apple. It pools idle Mac GPUs into a shared compute cluster for ML inference.
There is no distributed execution of a single LLM across multiple GPUs using tensor parallelism here. Instead, it relies on task-level parallelism-breaking down a large workload into independent subtasks that run across separate machines. For example, generating embeddings for a million documents.
My university ran its render farm across idle workstations using the screensaver back in early 2000. Same concept.
So basically works the same way as Folding@Home?
Embedding@Work
HotBackpack@Commute
DeadBattery@Work
Only on the same local network I guess.
or distributed.net
I guess for companies this can be nice? Run some inference in the off-hours on the machines that you already have. Could be useful for analytical tasks that don't require to be instant. On the technical side this doesn't seem that groundbreaking for me though.
My warm take is that Apple is leaving a lot of money on the table by not investing in creating an independent supply chain for their chips and building their own cloud. They arguably had the first mover advantage when it came to general purpose arm compute; all they had to do was flood the market and make it easy for anyone to rent it. Not only would they corner a part of the market but perhaps ease demand pressure on other chip manufacturers too.
Apart from straight up buying TSMC's or Samsung's fabs I don't see a way of building a vertically integrated high-end chip supply chain for Apple. At least not on timeframes measured below a decade. And on those time frames the current supply issues will probably be resolved by companies who put all their effort into it instead of just tweaking their bottom line.
TBH Im surprised they havent already bought one of these companies.
There is zero chance Taiwan or South Korea would allow this. It would be blocked on National Security grounds for each respective company/country.
It might actually serve as an insurance policy of sorts.
I don't think they would be able to buy any of these. It would have been blocked by multiple regulators.
They've had a great deal of success playing them off against each other.
because their entire thing is to focus on a few product lines... I'm not surprised at all
My guess is that they have challenges scaling the production anyway (6-16 weeks wait time for Studios), and also they would leave money in the table if they just released chips. I would assume that once they scale the production they will get back to the server game - MacOS server racks, or something more inventive like MacOS supercomputers running on a ton of prev gen chips ;)
My guess is that it's already hard for them to get as many chips fabricated for their devices, which is still their main source of income so far.
Maybe their chip team is already on the work, or already made, a server chip for AI purposes used internally, and doesn't have to talk about it yet.
https://appleinsider.com/articles/26/08/24/this-is-the-first...
They don't get enterprise, A/UX, mkLinux, OS X Server, Mac Pro tower, all gone now.
Swift's main reason to go open source and have good Linux support was naturally for app developers to be able to use it on server side, which naturally wasn't going to be macOS.
I macOS wasn't required for developing iDevices apps, they would surely sell even less desktops.
We did a little demo/have a patent for a similar idea using idle GPUs on Mercedes vehicles once upon a time - https://patents.google.com/patent/US20230281046A1/en
As with all similar SETI@home approaches, this paper does not address the energy cost.
Yes, we can distribute tasks to idle machines in homes and on office desktops, but it is often much more expensive than sending it to a data center where power is cheaper and the hardware is more efficient.
It would be so incredibly cool if we finally had an accessible consumer-accessible way to turn a network of computers on a network into a supercomputer. A household has a child who gets into 3D artwork and wants to render something? People can opt their tablets, phones, laptops, whatever to crunch out some frames overnight while not being used.
There is a startup working on this called Distributive I used to work for - their compute nodes are based on js/wasm runtimes so you just need a web browser to turn a device into a compute node...
until you get a teen obsessed with 3d rendering then they're up all night finding a way to convert manga into 3d scenes and your old laptop is running 100% cpu trying to keep up. xDD
The idealized version of this in my mind has a consent-first interface which makes it easy to set boundaries and limits and wouldn't burn out the machine as a default
This is basically what seti and the computing @home projects did. Just doesn't get as much support outside of hobbiest and institutions.
[delayed]
I remember seeing this at a presentation two or three years ago. I’m surprised it wasn’t rolled out right after?
They'll throw this together but still not sell you something you can stick in a rack ?
That seems to be the point: you leverage existing workstations on your corporate network and run compute batches at night while they're idle. You don't have to buy any extra servers for your low-priority AI workloads.
We were doing this decades ago with engineer's HP C3600s under their desks. It wasn't AI, just low-priority HPC / fluid stuff batched out to hundreds of workstations.
That was the original pitch for Ian Murdock's Progeny startup in the late 90s: a Linux-based distributed filesystem for corporate desktops to boot into overnight for distributed computing.
Imagine if Apple made a GENERIC distributed compute framework to leverage idle computing power from Macs for distributed Rendering/Compiling/etc use cases. I'm sure Apple could convince Adobe and others to support this framework for their compute-intensive products and create a really interesting ecosystem for it.
Then universities and business could reduce their need for cloud and have a reason to put that spending towards higher end Macs...
Literally built into it since 10.6.
https://developer.apple.com/documentation/dispatch
Darkbloom is already doing that today (darkbloom.ai)
I don't get it. In the paper it sounds like it's "just" a CRUD DB, then you have some fleet of Macs, and they store inputs and outputs in S3. What's the innovation here? Not trying to poo on this, but it looked like the most basic and obvious approach.
That's why the button is on the underside.
There are a lot of parallels between the DGX (and clones) series devices and these Apple devices, maybe it would be possible to rope in the DGX boxes as well. There's lots of them out there and I'm pretty sure not all of them have high utilization.
Would love to build something like this but for classification models that run on CPU. Like a “Classify @ Home” p2p compute network, to which people could contribute their machines and see what work is being done
Building the classification part now :) https://jeffyclassify.com/
Paper:
https://arxiv.org/pdf/2610.12970
Shortest promoted paper I've seen from a FAANG.
Apple rediscovering HPC clusters, but without OS X Server to serve alongside it.
It's not a novel idea, but its provable that someone can take this same concept and do something truly groundbreaking. I wonder if there's value in the idea that you can join a supercomputer network of MAC/Nvidia GPUs as a way of getting off cloud and into "our cloud". As long as you offer compute, you have credit into the system to be able to support your own workloads that can't be done on just your hardware. Need to address concerns about privacy, abuse, etc, but Apple's idea here has some merit if applied right.
Interesting, so this is basically Apple's version of exo ? https://github.com/exo-explore/exo
Reading the “paper”, this is just a job runner built on Ollama. Exo, and the teams at Apple that built the foundations Exo uses, actually use modern distributed compute.
I don't get why they didn't use llama.cpp instead.
I’m a bit disappointed in the lack of depth (and use of Ollama): https://arxiv.org/html/2610.12970v1
Apple has released some small models previously that seemed genuinely great, along with some quality research/efforts. I’m just not seeing the same level of depth here, am I missing something?
I think it's basically just a write-up of something they're already using internally.
true, shame on apple for the paper quality
Why is this a paper? Should've just been a blogpost. Maybe I don't understand academia
I built something very adjacent to this right before leaving Apple, same name, handed off to my team.
I’m very curious if that project evolved to this……..going to message a few friends now heh
Apple has reinvented cycle scavenging about 40 years later.
If I can get paid for heating my home with LLM queries this winter, I'm all for it.
Sounds similar to Salad (salad.com), except for the differing hardware.
Is this opt-in or opt-out?
I’ll opt-in to working at Apple
This project sounds good.
What is it actually like?
internal system, so the IT/HR department is the solution to leechers.
nothing new here.
>Apple steals your electicity while you take a dump