llama.cpp
llama.cpp copied to clipboard
Feature Request: webui: add parsing progress
Prerequisites
- [x] I am running the latest code. Mention the version if possible as well.
- [x] I carefully followed the README.md.
- [x] I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
- [x] I reviewed the Discussions, and have a new and useful enhancement to share.
Feature Description
Adding a statisics with speed of parsing promt token, like webui has for token generation.
Ideally show:
context: xxx / max (Y%)input: ... / xxx (Z%)A.B t/s
Motivation
Right now webui has nice progress and speed for token generation, but when it on parsing large input, for 10k or 20k tokens... user see just Processing... for quite a while.
Possible Implementation
No response
test it and let me know if it fulfills your expectations for this enhancement @catap