←back to thread

GGML – AI at the Edge

(ggml.ai)
899 points georgehill | 3 comments | 06 Jun 23 16:50 UTC | HN request time: 1.125s | source
Show context
sva_ ◴[06 Jun 23 20:36 UTC] No.36218756[source]▶
Really impressive work and I've asked this before, but is it really a good thing to have basically the whole library in a single 16k line file?
replies(3): >>36219310 #>>36220176 #>>36227321 #
1. regularfry ◴[06 Jun 23 21:24 UTC] No.36219310[source]▶
It makes syncing between llama.cpp, whisper.cpp, and ggml itself quite straightforward.

I think the lesson here is that this setup has enabled some very high-speed project evolution or, at least, not got in its way. If that is surprising and you were expecting downsides, a) why; and b) where did they go?

replies(1): >>36221083 #
2. mhh__ ◴[07 Jun 23 00:28 UTC] No.36221083[source]▶
https://git-scm.com/book/en/v2/Git-Tools-Submodules
replies(1): >>36224577 #
3. regularfry ◴[07 Jun 23 09:08 UTC] No.36224577[source]▶
Or... `cp`. It's fine.