Latest
The surprising depths of prompt caching
Prompt caching looks like a token discount. Underneath, it is KV tensors, prefix trees, inference economics, and a privacy model hiding in plain sight.
We can't find the internet
Attempting to reconnect
Something went wrong!
Attempting to reconnect
opub journal
The latest launch updates, engineering tales, and stories about the open source projects putting funded model tokens to work.
Featured
Prompt caching looks like a token discount. Underneath, it is KV tensors, prefix trees, inference economics, and a privacy model hiding in plain sight.
All posts
1 of 3Subscribe to the newsletter
Rare and concise letters with our latest writing, sponsorships, and updates.