Files
mlc-ai--web-llm/examples/get-started-latency-breakdown/README.md
T
wehub-resource-sync f73e710e38
Build site and push to gh-pages / Build site (push) Waiting to run
Build / build (push) Waiting to run
Linter / lint (push) Waiting to run
Security / dependency-review (push) Waiting to run
Security / npm-audit (push) Waiting to run
Security / codeql (push) Waiting to run
Tests / test (push) Waiting to run
chore: import upstream snapshot with attribution
2026-07-13 12:42:51 +08:00

16 lines
547 B
Markdown

# WebLLM Get Started App
This folder provides a minimum demo to show WebLLM API in a webapp setting with
collection of latency statistics for individual token sampling steps.
To try it out, you can do the following steps under this folder
```bash
npm install
npm start
```
Note if you would like to hack WebLLM core package.
You can change web-llm dependencies as `"file:../.."`, and follow the build from source
instruction in the project to build webllm locally. This option is only recommended
if you would like to hack WebLLM core package.