Tianqi Chen comments

Results 637 comments of


                                            Tianqi Chen

[Relax][Bugfix] Annotate ComputePrimValue output as host function

due to recent ci restart, likely we need to close and re create another pr for the ci to get retriggerd

[WebGPU] Update error messages to be more user-friendly

@tvm-bot rerun

[WebGPU] Update error messages to be more user-friendly

@tvm-bot rerun

[CI] [doc] fix the dead link of resnet and mobilenet

@tvm-bot rerun

[Tracking] Android build refactor: publish ready-made maven artifacts

We migrated to a sdk based approach where the library will be packaged through mlc LLM package command

[Question] How to generate conversational template with more than one input

Thanks for asking, this is an interesting usecase. I believe you can use OpenAI style prompts(and just use the original llama3 conv template) via: ```python user_prompt=f""" Generate a SQL query...

[Question] How to generate conversational template with more than one input

thanks @Faolain for confirming, glad it works

[Question] How do you convert .bin files to wasm. Also where are TVM_HOME and MLC_HOME located?

you can use the pip insall, but still need to obtain a copy of the source code

[Bug] Can't finish the build process on windows

the error was due to lack of cmake dependency, can you install cmake via conda?

[Bug] Can't finish the build process on windows

https://llm.mlc.ai/docs/deploy/android.html#additional-guides-for-windows-users Please try the above tips, just confirmed with a windows