Petals is from 2022. Nowadays intelligence of smaller models, quantization techs, and optimizations to run models faster on consumer GPUs have improved a lot.
For distributed inference of smaller LLMs and diffusion models that fits in one consumer GPU rather than splits on multiple machines, there are already pretty good solutions such as AI Horde (formerly Stable Horde) [0]. Notably, it's the default provider that powers SillyTavern. It also has an interesting economy model of kudos.
The recently discussed https://meshllm.cloud/ is the one I've been playing with but don't have the hardware to try with a model split between nodes, which apparently is supported and just not part of the public demo.
It's an interesting concept but the timing is probably too early. If more people had reliable low latency gigabit or ideally 10gbit throughput, then it might start to approach feasibility. There's other blockers too, but that springs to mind immediately.
It's cool to imagine a planet wide neural network interconnected with fiber - the nervous system of a planetary intelligence. But perhaps mushrooms do that already (Alpha Centauri ever relevant).
> [...] volunteers can donate their hardware power to tackle a portion of a text-generating workload and team up others to complete larger tasks, similar to Folding@home and other distributed compute setups.
Distributed training is much harder than distributed inference but not impossible. See the recent development of DiLoCo at Nous Research and Prime Intellect.
I have been thinking of something on these lines but with much smaller models. The entire model has to fit on a single computer. Host owner would choose the model they prefer, perhaps because they already use it. Then it is more about utilizing the GPU for LLM requests.
Peer to peer, consumers get to route their request to a host with compatible model. Consumers have to also contribute GPU but it does not have to be equal - I have not thought through the fairness part. Perhaps initially it starts with "create your friends group and have access to all the host nodes".
AI Horde has some measures to prevent Sybil attack that returns wrong results, but not enforce zero data retention. Prompts belong to the whole open source community. For example https://huggingface.co/datasets/la-ji/sd-prompt-in-the-wild
I do not know what/who Sybil is but yes, there is a lot of plumbing in order to make sure that host nodes are ZDR* compliant and much more. Zero visibility of source prompt.
Also, this is the reason I want to start with trust based groups only - invite people you already know. I have friends who have Macs with 32GB or 48GB unified memory but sending prompts to them is not a out of the box thing.
> A Sybil attack is a type of attack on a computer network service in which an attacker subverts the service's reputation system by creating a large number of pseudonymous identities and uses them to gain a disproportionately large influence.
I've occasionally written comments about the difficult of achieving proof-of-useful-work mechanisms and I should probably find or write a standard post about this question.
In order to be as decentralized as Bitcoin and related PoW mechanisms, a proof-of-work mechanism should have
* the ability to create an unbounded number of instances of the problem deterministically from numeric seeds
* the ability to scale difficulty up and down using a difficulty parameter
* in a way where anyone can easily confirm that a given problem instance corresponds to a given seed, and anyone can easily confirm that a given solution correctly solves a given problem instance
I'm not aware of a proof-of-useful-work mechanism that meets these criteria. (I'm also not aware of an argument that it's impossible to have one. Zero-knowledge proofs might actually go far toward making it possible in the future. but it's kind of complicated.)
You can easily build a localized, access-controlled compute grid using Apple Silicon hardware. Haven't tested but as far as I can see, the key to making it performant would be keeping full models resident on individual nodes rather than attempting to distribute the tensor processing across the network.
For distributed inference of smaller LLMs and diffusion models that fits in one consumer GPU rather than splits on multiple machines, there are already pretty good solutions such as AI Horde (formerly Stable Horde) [0]. Notably, it's the default provider that powers SillyTavern. It also has an interesting economy model of kudos.
[0] https://stablehorde.net/
It's cool to imagine a planet wide neural network interconnected with fiber - the nervous system of a planetary intelligence. But perhaps mushrooms do that already (Alpha Centauri ever relevant).
Doesn't look like it's very active nowadays: https://github.com/bigscience-workshop/petals
Article with more details: https://techcrunch.com/2022/12/20/petals-is-creating-a-free-...
> [...] volunteers can donate their hardware power to tackle a portion of a text-generating workload and team up others to complete larger tasks, similar to Folding@home and other distributed compute setups.
Run LLMs at home, BitTorrent‑style - https://news.ycombinator.com/item?id=37546810 - Sept 2023 (125 comments)
Peer to peer, consumers get to route their request to a host with compatible model. Consumers have to also contribute GPU but it does not have to be equal - I have not thought through the fairness part. Perhaps initially it starts with "create your friends group and have access to all the host nodes".
Also, this is the reason I want to start with trust based groups only - invite people you already know. I have friends who have Macs with 32GB or 48GB unified memory but sending prompts to them is not a out of the box thing.
* typo
https://en.wikipedia.org/wiki/Sybil_attack
---
[0]: https://www.gnus.ai/
You could even hand out some kind of digital 'currency' to the people proportional to the amount of work their doing!
In order to be as decentralized as Bitcoin and related PoW mechanisms, a proof-of-work mechanism should have
* the ability to create an unbounded number of instances of the problem deterministically from numeric seeds
* the ability to scale difficulty up and down using a difficulty parameter
* in a way where anyone can easily confirm that a given problem instance corresponds to a given seed, and anyone can easily confirm that a given solution correctly solves a given problem instance
I'm not aware of a proof-of-useful-work mechanism that meets these criteria. (I'm also not aware of an argument that it's impossible to have one. Zero-knowledge proofs might actually go far toward making it possible in the future. but it's kind of complicated.)