Hacker News new | ask | show | jobs
by ronsor 974 days ago
I disagree. llama.cpp[0] is a good counterpoint to this, since it uses a custom ML framework created from scratch. Despite not having the developer team of a large company, it still keeps up with many of the advancements in LLMs.

[0] https://github.com/ggerganov/llama.cpp
1 comments
elwypea 974 days ago
llama.cpp is not necessary for creating lots of demand for the chip it was originally written for (Apple M1), whereas new hardware vendors need to demonstrate they can plugin to existing tools to generate enough demand to ship in volume.
link
ronsor 973 days ago
> lots of demand for the chip it was originally written for (Apple M1)

To be fair, the M1/M2 chip can't be purchased or used separately from the Mac, unlike GPUs or socketed CPUs, and demand for Macs is already fairly high.

link