Tianqi Chen
Tianqi Chen
Re: webgpu WASI. I think there are better person to champion WASI webgpu (e.g. @Kangz, @kvark) than myself. I would certainly love to help to make that happen, and provide...
For background, most of the web related APIs, e.g. WebGPU are designed to be async to begin with. So `wait_for_gpu` represent the original version of the API. The main purpose...
To give a bit more context about the sync to async, the code example below demonstrate one potential interface for such usage. ``` c++ // WASM source code to be...
thanks @dtkettler can you also let us know what is the model and prompt? having an example script would be helpful
llama3 should be fixed by latest version
Thanks @dtkettler , there are some fixes that just come in now, so please wait another day for the effect to kick into nightly. when runnning json mode, likely you...
@DiegoCao can you help to followup and add TP support?
@Hzfengsy seems alll deps are landed, let us followup
I am not sure what was happening on this case, perhaps it is related to come stale variant of compiler. we recently updated our android SDK https://llm.mlc.ai/docs/deploy/android.html please try follow...
Glad this is resolved. likely it was due to old ersion of the tvm