Hangrui Cao

icon company Carnegie Mellon University icon location Pittsburgh icon location CMU MS at SCS working on @acai-systems @mlc-ai | 2023 Amazon Summer Intern | 2021 Intern @intel-analytics @analytics-zoo Interested in Distributed ML

Results 11 comments of Hangrui Cao

next-simple chat - ReferenceError: require is not defined in ES module scope, you can use import instead

Looking into this!

next-simple chat - ReferenceError: require is not defined in ES module scope, you can use import instead

I've replicated the problem, will try to fix it

[Tracking] Model loading/caching enhancements

Hi David, thanks for offering the help! I'm looking into the TVMjs as well and we need to make changes in module TVMjs.

[Tracking] Model loading/caching enhancements

@DavidGOrtega I can work on C2 first and work on C4 after you built the indexDB and levels.

[Tracking] Model loading/caching enhancements

> Sorry for chiming in late. For the caching layer, ideally we would like something that comes with minimal dependency. Spefically, we should: > > * Make ArtifactCache https://github.com/apache/tvm/blob/main/web/src/runtime.ts#L991 an...

[Tracking] Model loading/caching enhancements

Hi @ethrx thanks! It requires some changes on the TVM side and I have started working on it

BufferSource argument is empty

Thanks, looking into it now

BufferSource argument is empty

@DavidGOrtega May I ask before the indexedDB pull request, does the problem for this BufferSource exist?

Support Qwen2-MoE Architecture

Got it, working on the TP support

[Bug] some Qwen-72B based llamafied models compatibility test

Thanks, working on reproduce that.