We’re moving fast to get it stable and usable. The goal is for this to be as simple as running Dropbox. Bear with us :)

    This enables you to run larger models
    than you would be able to on any single
    device.

If some layers of the neural network are on deviceA and some layers are on deviceB, wouldn't that mean that for every token generated, all output data from the last layer on deviceA have to be transferred to deviceB?

I wonder if training could be done in this way too.

Out of curiosity, would you ever support training or at least fine-tuning?

But I guess the final output needs to be sent back to the first node before it can continue. So if there are 50 nodes with a latency of 40ms each, each token would take 2s to process.

For example, if I have a few servers, laptop (connected to power) as well as a desktop PC and they’re all connected to a fast local network, it’d be great to distribute the task of rendering a video or working with archive files across all of them.

Perhaps you'd like to plug it into a toolchain that runs faster than API calls can be passed over the network? -- eventually your edge hardware is going to be able to infer a lot faster than the 50ms+ per call to the cloud.

Maybe you would like to prevent the monopolists from gaining sole control of what may be the most impactful technology of the century.

Or perhaps you don't want to share your data with Microsoft & Other Evils (formerly known as dont be evil).

You might just like to work offline. Whole towns go offline, sometimes for days, just because of bad weather. Nevermind war and infrastructure crises.

Or possibly you don't like that The Cloud model has a fervent, unshakeable belief in the propaganda of its masters. Maybe that propaganda will change one day, and not in your favor. Maybe you'd like to avoid that.

There are many more reasons in the possibility space than my limited imagination allows for.

I'd rather have a weaker model which I can always rely on being available than a strong model which is hosted by a third party service that can be shut down at any time.

Every LLM project I’ve worked with has an abstraction layer for calling hosted LLMs. It’s trivial to implement another adapter to call a different LLM. It’s often does as a fallback, failover strategy.

There are also services that will merge different providers into a unified API call if you don’t want to handle the complexity on the client.

It’s really not a problem.

You've got a plethora of cloud providers, all of them aligned to a foreign country's laws and customs.

If you can choose between Anthropic, OpenAI, Google, and some others... well, that's really not a choice at all. They're all in California. What good does that do an Austrian or an Australian?

This is interesting. Is that based on any upcoming technology improvement already in the works?

LLMs are great as routers, only rarely are they good doing something on their own.

Obvious answer: because it's not free, and it's not cheap.

If you're playing with a UI library, lets say, QT... would you:

a) install the community version and play with ($0)

b) buy a professional license to play with (3460 €/Year)

Which one do you pick?

Well, the same goes. It turns out, renting a server large enough to run big (useful, > 8B) models is actually quite expensive. The per-api-call costs of real models (like GPT4) adds up very quickly once you're doing non-trivial work.

If you're just messing around with the tech, why would you pay $$$$ just to piss around with it and see what you can do?

Why would you not use a free version running on your old PC / mac / whatever you have lying around?

> I used to be excited about running models locally

That's an easy position to be one once you've already done it and figured out, yes, I really want the pro plan to build my $StartUP App.

If you prefer to pay for an online service and you can afford it, absolutely go for it; but isn't this an enabler for a lot of people to play and explore the tech for $0?

Isn't having more people who understand this stuff and can make meaningful (non-hype) decisions about when and where to use it good?

Isn't it nice that if meta released some 400B llama 4 model, most people can play with it, not just the ones with the $7000 mac studio? ...and keep building the open source ecosystem?

Isn't that great?

I think it's great.

Even if you don't want to play, I do.

"What if I want to play around with really PERSONAL stuff."

I've been keeping a digital journal about my whole life. I plan to throw that thing into an AI to see what happens, and you can be damn sure that it will be local.

The startup costs for just messing around at home are huge: purchasing a server and gpus, paying for electricity, time spent configuring the api.

If you want to just mess around, $100 to call the world’s best api is much cheaper than spending $2-7k Mac Studio.

Even at production level traffic, the ROI on uptime, devops, utilities, etc would take years to recapture the upfront and on-going costs of self-hosting.

Self hosting will have higher latency and lower throughput.

pacman -S ollama

ollama serve

ollama run llama3

My basic laptop with about 16 GB of RAM can run the model just fine. It's not fast, but it's reasonably usable for messing around with the tech. That's the "startup" cost. Everything else is a matter of pushing scale and performance, and yes that can be expensive, but a novice who doesn't know what they need yet doesn't have to spend tons of money to find out. Almost any PC with a reasonable amount of RAM gets the job done.

A novice isn't going to know what they need because they don't know what they don't know. Try asking a question to LLaMA 3 at 8 billion and the same question to LLaMA 3 at 70 billion. There is a night and day difference. Sonnet, Opus and GPT-4o run circles around LLaMA 3 70b. To run LLaMA at 70 billion you need serious horse power as well, likely thousands of dollars in hardware investment. I say it again... the calculus in time, money, and effort isn't favorable to running open models on your own hardware once you pass the novice stage.

I am not ungrateful that the LLaMA's are available for many different reasons, but there is no comparison between quality of output, time, money and effort. The API's are a bargain when you really break down what it takes to run a serious model.

A lot of other things are possible with LLMs using the context window and completion, thanks to their "zero shot" learning capabilities. Which is also what RAG builds upon.

They do not compare to the giant models like Claude Sonnet and GPT4 when it comes to trying to use them for complex things.

I continue to use both local models and the commercial cloud offerings, but I think anyone who suggests that the small local models are on par with the big closed hosted models right now is wishful thinking.

If your metric is quality of output, time, money and tok/s, there is no comparison; Local models just aren't there yet.

No, they are zero.

Most people have extra hardware lying around at home they're not using. It costs nothing but time to install python.

$100 is not free.

If you can't be bothered, sure thing, slap down that credit card and spend your $100.

...but, maybe not so for some people?

Consider students with no credit card, etc; there are a lot of people with a lot of free time and not a lot of money. Even if you don't want to use it do you do seriously think this project is totally valueless for everyone?

Maybe, it's not for you. Not everything has to be for everyone.

You are, maybe, just not the target audience here?

The difference between an open model running on a $100 computer and the output from GPT4 or Claude Sonnet is huge.

I use local and cloud models. The difference in productivity and accuracy between what I can run locally and what I can get for under $100 of API calls per month is huge once you get past basic playing around with chat. It’s not even close right now.

So I think actually you are not the target audience for what the parent comments are taking about. If you don’t need cutting edge performance then it’s fun to play with local, open, small models. If the goal is to actually use LLMs for productivity in one way or another, spending money on the cloud providers is a far better investment.

Exceptions of course for anything that is privacy-sensitive, but you’re still sacrificing quality by using local models. It’s not really up for debate that the large hosted models are better than what you’d get from running a 7B open model locally.

This is undoubtedly entitled, but thinking to yourself huh, I think it's time to try out some of this machine learning stuff is a pretty inherently entitled thing to do.

I don't think having an old phone is particularly entitled.

I think casually slapping down $100 on whim to play with an API... probably, yeah.

/shrug

I run my own models, but the truth is most of the time I just use an API provider.

TogetherAI and Groq both have free offers that are generous enough I haven't used them up in 6 months of experimentation and TogetherAI in particular has more models and gets new models up quicker than I can try them myself.

Our demo site uses two NVIDIA GeForce RTX 3090 and our whole team is hammering it all day. The only problem is occasionally high GPU temperature.

I don't think the picture is as bleak as you paint. I actually expect Moore's Law and better AI architectures to bring on a self-hosted AI revolution in the next few years.

[^1] Hey! If you know of spell-checking-tuned LLM models, I'm all ears (eyes).

You could probably train any recent LLM to be better than a human at spelling correction though, where "better" might be a vague combination of faster, cheaper, and acceptable loss of accuracy. Or maybe slightly more accurate.

(A lot of people hate on LLMs for not being perfect, I don't get it. LLMs are just a tool with their own set of trade offs, no need to get rabid either for or against them. Often, things just need to be "good enough". Maybe people on this forum have higher standards than average, and can not deal with the frustration of that cognitive dissonance)

If you don't care about running it locally, just spend it online. Everything is good.

But you can run it locally already. Is it cheap? No. Are we still in the beginning? yes. We are still in a phase were this is a pure luxury and just getting into it by buying a 4090, is still relativly cheap in my opinion.

Why running it locally you ask? I personally think running anythingllm and similiar frameworks on your own local data is interesting.

But im pretty sure in a few years you will be able to buy cheaper ml chips for running models locally fast and cheap.

Btw. aat least i don't know a online service which is uncensored, has a lot of loras as choice and is cost effective. For just playing around with LLMs for sure there are plenty of services.

Not sure why your throwing your hands up because this is a step towards solving your problem.

I'm saying because I've had the exact OPPOSITE thought. The intersection of Moore's Law and the likelihood that these things won't end up as some big unified singularity brain and instead little customized use cases make me think that running at home/office will perhaps be just as appealing.

Running locally, you can change the system prompt. I have Gemma set up on a spare NUC, and changed the system prompt from "helpful" to "snarky" and "kind, honest" to "brutally honest". Having an LLM that will roll its eyes at you and say "whatever" is refreshing.

Copilot+ PC’s, which all run models locally, have the best battery life of any portable PC devices, ever.

These devices have in turn taken a page out of Apple Silicon’s playbook. Apple has the benefit of deep hardware and software integration that no one else has, and is obsessive about battery life.

It is reasonable to think that battery life will not be impacted much.

Sorry, I can't let misinformation like that slide.

Cloud cost/benefit ratio is not good in many circumstances.

For hobbyists it works well because you run your job for very brief periods and renting is much cheaper than buying in those cases. Similarly, if your business usage is so low as to be effectively run once per day then cloud has major benefits.

However, if you are doing any kind of work that consumes more than 8hrs of computer time in a day, cloud is going to start being much more expensive.

The exact cost/benefit depends on the SKU and I'm mostly talking about CPU/Memory/Storage- for managed services like databases it's significantly worse, and I'm comparing to rented servers not self-hosting at home, which is significantly cheaper still.

Local hardware has downsides (availability, inflexibility), but it's faster and cheaper in almost all real workload scenarios where the compute would otherwise be completely idle/turned off >90% of the time.

Apple can fine-tune a local LLM to respond to a catalog of common interactions and requests but it’s hard to see anyone else deploying fine-tuned models for non-technical audiences or even for their own purposes when most of their needs are one-off and not recurring cases of the same thing.

Edit: it's also a matter of scale. You probably have a small number of small/slow devices in a consumer network versus a lot of large/fast devices in your enterprise cluster.

Inference across O(N) pre-trained hidden layers isn't exactly an "embarrassingly parallel" problem, but it is an "embarrassingly pipeline-able" problem (in the CPU sense of "pipelining.") Each device can keep just one or a few layers hot in their own VRAM; and also only needs to send and receive one small embedding (<1MB) vector per timestep — which is so trivial that it's easily achievable in realtime even if all the devices are on wi-fi, talking to the same router, in your "noisy" apartment where 100 other neighbours are on the same bands.

(To put it another way: running a single inference job, has more forgiving realtime latency+throughput requirements than game streaming!)

Assuming that you have a model that's too big for any of your home machines to individually hold; and that all you care about is performance for single-concurrent-request inference on that model — then in theory, you just need one GPU of one node of your homespun Beowulf GPU cluster to have enough VRAM to keep the single largest layer of your model always-hot; and then other smaller devices can handle keeping the smaller layers always-hot. And the result should be faster than "overloading" that same model on that single largest-VRAM device and having some layers spill to CPU, or worse yet, having the GPU have to swap layers in and out repeatedly with each inference step.

(Also, if you're wondering, in the case where a single machine/node has multiple GPUs — or a GPU+VRAM and also a CPU+RAM! — you can treat this as no different than if these were multiple independent nodes, that just-so-happen to have a very efficient pipeline communication channel between them. As the VRAM+computation cost of running inference far outweighs the communication overhead of forward propagation during inference, a home-network inference-pipelining cluster scheduler like this project, would still likely "schedule" the model's layers purely in consideration of the properties of the individual GPU+VRAM (or CPU+RAM), rather than bothering to care about placement.)

---

That being said, AFAIK training is "pipeline parallelizable" exactly as inference is. And people training models do do this — but almost always only across multiple top-of-the-line GPUs in one machine; not across multiple machines.

When you think about what pipelining achieves for training — all you get is either:

1. the ability to use a bunch of small-aggregate-VRAM nodes to achieve the aggregate training capacity of fewer, larger-aggregate-VRAM nodes — but with more power consumption = higher OpEx; and where also, if you scale this to O(N), then you're dumping a quadratic amount of layer-propagation data (which is now both forward-prop and backprop data, and backprop data is bigger!) over what would likely be a shared network just to make this work. (If it's not a shared network — i.e. if it's Infiniband/other RDMA — then why did you spend all that CapEx for your network and not on your GPUs!?)

2. the ability to pipeline a bunch of large-aggregate-VRAM nodes together to train a model that will then never be able to be deployed onto any single node in existence, but can instead only exist as a "pipelined inference model" that hogs O(log N) nodes of your cluster at a time for any inference run. Which makes cluster scheduling hell (if you aren't just permanently wiring the scheduler to treat O(log N)-node groups as single "hyper-nodes"); makes it so that you'll never be able to practically open-source the model in a way anybody but other bigcorps could ever run it (if that's something you care about); and very likely means you're cutting the concurrent-inference-request-serving capacity of your huge expensive GPU cluster by O(log N)... which the product team that allowed that cluster to be budgeted is really not gonna like.

That being said, I imagine at some point one of these proprietary "Inference-as-a-Service" models has been trained at a layer size that puts it into pipelined-inference-only territory, temporarily. Doing so would be the ML engineer's equivalent to the CPU engineer's "we have no fundamentally clever advance, so this quarter we'll just crank up the clock frequency and deal with the higher TDP." (Heck, maybe GPT-4o is one of these.)

---

What people with GPU clusters want, is 1. for the output of the process to be a model that runs on a single (perhaps multi-GPU) node; and 2. for the process itself to be mostly-shared-nothing with as little cross-node communication burden as possible (such that it's just a question of building highly internally communication-efficient nodes, not so much highly-communication-efficient clusters.)

And both of those goals are achieved by sizing models so that they fit within a single node; continuously fanning out streams of training data to those nodes; and then periodically fanning back in model-weights (or model-weight deltas) in an AllReduce operation, to merge the learning of O(N) independently-training nodes to become the new baseline for those nodes.

(If you'll note, this architecture doesn't put any latency requirements on the network, only some monstrous throughput requirements [at the fan-in step] — which makes it a lot easier to design for.)

Edit: I don't know where else to begin. It's a runtime that has lightweight processes, excellent observability, absurdly good fault tolerance, really nice programming languages and so on. It's designed for distributed computing.

This seems like a good option for a switch.

Do you know if any of these can run on Apple/Android devices?

On Android you've got Termux in F-Droid and can pull in whatever BEAM-setup you want. That's how I first started dabbling with the BEAM, I was using a tablet for most of my recreational programming and happened to try it out and got hooked.

Erlang is pretty weird, but it just clicks for some people so it's worth spending some time checking it out. Elixir is a really nice Python-/Ruby-like on the BEAM, but with pattern matching, real macros and all the absurdly powerful stuff in the Open Telecom Platform.

The markup on Apple hardware is so big that I just don't think "cheapish" will ever be a way to describe the position they hold in the AI market. Apple's current budget lineup gets smoked by an RTX 3060 in a cheap Linux homeserver; the bar for high-value AI has been raised pretty high.

so by definition you need (1) good internet 20mb/s+ and (2) good devices.

This thing will not go any further than cool demo on twitter. Please prove me wrong.

The way this works is that each device holds a partition of the model (for now a continuous set of layers). E.g. let's say you have 3 devices and the model is 32 layers. Device 1 could hold layers 1-10, device 2 holds 11-20 and device 3 holds 21-32. Each device executes the layers it's responsible for and passes on the output of its last layer (the activations) to the next device.

The activations are ~8KB for Llama-3-8B and ~32KB for Llama-3-70B (it's linear in the number of parameters in that layer and Llama-3-70B has more layers). Generally the larger the model gets (in terms of parameters), the more layers it ends up having, so we end up with sub-linear scaling so I expect Llama-3-405B to have activations on the order of ~100KB.

This is totally acceptable to send over a local network. The main issue you run into is latency, not bandwidth. Since LLMs are autoregressive (tokens are generated serially), additional latency limits throughput. However, over a local network latency is generally very low (<5ms in my experience). And if not, it's still useful depending on the use-case since you can get a lot of throughput with pipeline parallelism (overlapping requests): https://pytorch.org/docs/stable/pipeline.html

Edit: to add on, the only evidence that this runs anywhere but Apple Silicon is the maintainer's Twitter where they show it running on two Macbook Pros as well as other devices. I'm not sure how many of those devices are not ARM.

I'm not throwing shade at the concept the author is presenting, but I'd appreciate if they could slow down functional commits (he is writing them right now as I type) and truthfully modify the documentation to state which targets are actually able to run this.