Tianqi Chen comments

Results 637 comments of


                                            Tianqi Chen

Does mlc-llm support nv gpu using CUDA instead Vulkan

most recent gpu drivers usually automatically comes with vulkan support

Missing features in Android

Thank you for the suggestions, I am marking the issue as temporary inactive, we are keeping inactive issues closed so we can open new ones. More recently we are adding...

how to build mlc-llm-cli on Linux

You need to set USE_CUDA=ON when compiling `mlc_llm`

how to build mlc-llm-cli on Linux

The cli is now deprecated in the new version, checkout https://llm.mlc.ai/docs/deploy/cli.html for latest instruction

Error: Cannot find PackedFunc vm.builtin.null_value in either Relax VM kernel library

closing as the latest version resolved the problem.

Slow Vicuna vulkan performance with self-built build.py model.

This may indeed be a regression, since all the dispatches are in the repo. Opening for now and let us confirm

Slow Vicuna vulkan performance with self-built build.py model.

cc @MasterJH5574

Slow Vicuna vulkan performance with self-built build.py model.

The latest version should resolved this

PackagesNotFoundError: mlc-chat-nightly

Atm we do not yet have prebuilt for jetson, but you can try to build from source

Avoid reloading shards in different tabs

ServiceWorker is now supported