Skip to content
Better HN
Top
New
Best
Ask
Show
Jobs
Search
⌘K
0 points
mchiang
10mo ago
0 comments
Save
Share
This is just wrong. Ollama has moved off of llama.cpp and is working with hardware partners to support GGML.
https://ollama.com/blog/multimodal-models
0 comments
3 comments · 2 top-level
default
top
newest
oldest
paulsmal
10mo ago
· 1 in thread
is it?
https://github.com/ollama/ollama/blob/main/llm/server.go#L79
mchiang
OP
10mo ago
we keep it for backwards compatibility - all the newer models are implemented inside Ollama directly
polotics
10mo ago
can you substantiate this more? llama.ccp.is also relying on ggml
j
/
k
navigate · click thread line to collapse
