A. F. Dudley

Yes. your line (with the typo fixed): `curl --output - http://localhost:5001/api/v0/block/get?arg=z45oqTS56MVrDkBQoQFs5mcxLHty2msTu2D3cJfdZfFsirxKnaN | eth-ipld block` returns: ` % Total % Received % Xferd Average Speed Time Time Time Current Dload Upload...

Thanks, I was able to replicate that with a more recent block.

@hermanjunge you were looking into adding postgres support to go-ethereum via https://github.com/ethereum/go-ethereum/tree/master/ethdb https://github.com/ethereum/go-ethereum/issues/2690 Why was that strategy abandoned and this one adopted? It seems like support `ipfs dag put` from...

We should discuss further in slack, but we are currently working on a filecoin grant to add the indexing required to support this sort of usage. https://github.com/vulcanize/filecoin-indexing/issues/4

What's the status of this?

I assume you have a single switch between all the devices? which model did you test with? What happens when you try with llama 1b?

> But it is theoretically a nice option to not have more filesystem cruft if you just want latest info. Do we rule that out as an option? Or re-architect...

This sounds very interesting and also like an almost completely different project? What parts of the existing codebase would your proposal share?

Can you confirm mlx works on an Asahi Linux based distro?

My guess is that's not enough RAM. I have the same problem. https://www.substratus.ai/blog/calculating-gpu-memory-for-llm I'm still trying to figure out how to benchmark this system. when using llama 3.2 1B adding...