Skip to content

Conversation

@ngxson
Copy link
Collaborator

@ngxson ngxson commented Dec 11, 2024

Important

You need to rm -rf build or make clean, then reconfigure cmake

Fix #10502

Also remove completion.js because it's quite messy to work with, it's now replaced with just 15 LOCs

Screenshot:

image image

On hover, it reveals more info:

image

@ngxson ngxson merged commit 235f6e1 into ggml-org:master Dec 11, 2024
6 checks passed
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Dec 20, 2024
* get rid of completion.js

* extract chat bubble to a component

* add tok/s info

* sync

* fix BASE_URL

* only extract timings when it's enabled

* fix auto scroll
tinglou pushed a commit to tinglou/llama.cpp that referenced this pull request Feb 13, 2025
* get rid of completion.js

* extract chat bubble to a component

* add tok/s info

* sync

* fix BASE_URL

* only extract timings when it's enabled

* fix auto scroll
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Feature Request: Add "tokens per second" information in the Web UI

2 participants