Comment by tokenmaxxinej
9 hours ago
input tokens are processed at 10-50 times the speed of output tokens since you can process then in batches and not one at a time like output tokens
9 hours ago
input tokens are processed at 10-50 times the speed of output tokens since you can process then in batches and not one at a time like output tokens
No comments yet
Contribute on Hacker News ↗