Tianqi Chen comments

Results 637 comments of


                                            Tianqi Chen

Phi-3-3.8 billion model [Model Request]

#2222

Prebuilt StableLM 1.6B model compilation not working

@tlopex can you look a bit into this model?

Prebuilt StableLM 1.6B model compilation not working

Thanks @tlopex !

[NOTICE] Transition from ChatModule to MLCEngine

@MikeLP yes, we should keep such customization

[NOTICE] Transition from ChatModule to MLCEngine

https://github.com/mlc-ai/mlc-llm/pull/2279 brings an initial iOS ver of MLCEngine

[NOTICE] Transition from ChatModule to MLCEngine

https://github.com/mlc-ai/mlc-llm/pull/2380 transitions iOS ChatApp to MLCEngine

[NOTICE] Transition from ChatModule to MLCEngine

https://github.com/mlc-ai/mlc-llm/pull/2410 transitions the android to the MLCEngine

[NOTICE] Transition from ChatModule to MLCEngine

We have completed the transition steps

AutoTVM optimization?

We are already applying auto-tune implicitly in many cases. The current mechanism dlight is already somewhat auto-tuned then coded into the rule, but indeed can be further tweaked, see examples...

AutoTVM optimization?

Relax is actually a better iteration from relay that address some of the long time compilation issues. The prebuilt are already better space so it is better optimized. You can...