Charlie Ruan
Charlie Ruan
## Overview There have been many great suggestions from the community regarding loading and caching model weights. This tracker issue compiles the suggestions and keeps track of the progress. ##...
Hi community, we recently updated our models' `mlc-chat-config.json` on hugging face to use the latest conversation template. The goal is to make templates more lightweight, hence not requiring an npm...
## Overview The goal of this task is to implement APIs that are [OpenAI API](https://platform.openai.com/docs/api-reference) compatible. Existing APIs like `generate()` will still be kept. Essentially we want JSON-in and JSON-out,...
This issue tracks the resolution to various front-end compatibility issues. ### Action items - [ ] Address `require()` issues - [ ] Address `perf_hooks` import issue - [ ] Add...
This is a pinned issue directed to the [Model Request Tracking Board](https://github.com/orgs/mlc-ai/projects/2). - To submit a model request, create a [Model Request issue](https://github.com/mlc-ai/mlc-llm/issues/new?assignees=&labels=new-models&projects=&template=model-request.md&title=%5BModel+Request%5D+) and it will automatically show up on...
Prior to this PR, when users `createEngine()` or call `reload()` with a model that is too large for the device, likely the device would keep generating, ignoring OOM issue and...
### Overview There are various runtime things we'd like to update and complete in WebLLM - [ ] Support grammar for Llama 3, hence update Hermes 2 support from Mistral...
We'd like to complete the following items for WebLLM documentation - [ ] Update github README: https://github.com/mlc-ai/web-llm - Also make sure npm package is sync'd https://www.npmjs.com/package/@mlc-ai/web-llm - [ ] Update...
This issue tracks various action items we would like to complete with regard to the features function calling and embeddings. ### Function calling (beta) We are calling it beta because...
Currently searching "WebLLM Chat" on Google would display the following weird result: This PR attempts to change that. All code is generated by Cursor and I have not checked whether...