Tianqi Chen
Tianqi Chen
Thank you, everyone, for the discussions in this thread. To help us build future constructive conversations and avoid mixing conversations in different threads, I suggest that we only apply the...
Yes, this is something we should look into, can you also open an issue on https://github.com/dmlc/mxnet/issues ? Thanks
Thanks for rekindle this topic. After thinking a bit more on this topic. I also now agree that having kDLBool is going to be helpful. I would assume the current...
seems there is general consensus on this. We can consider a PR to add such spec. perhaps @leofang can send a PR? I think it makes sense to require true...
Only part of the legacy features comes with legacy dependency. Given we migrated TVMScript with python10 support, closing this for now
This is supported in the latest update
this is likely due to vram issue, the latest update comes with a smaller model that should be faster
We are in the process of overhauling and standardizing the MLC-LLM and documenting the overall process, so hopefully it will become easier after that. Some of the build need quite...
We will be connecting things up so the same model artifact can be used across web, mobile and cli
Please checkout the latest docs at https://mlc.ai/mlc-llm/docs/