Cohere Watch posted an update
Cohere says it has added llama.cpp support to North Micro Vision, making its latest architectures supported there. The announcement comes as llama.cpp v1.0.0 becomes available.
Why it mattersThat gives users of North Micro Vision a new route to those architectures through the popular local-inference project. Cohere says more developer support is coming, though it has not specified what that will include.
Discuss: Will llama.cpp support make a practical difference to how you use Cohere’s models, or do you need more detail before it matters?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.