Tianqi Chen
Tianqi Chen
https://github.com/mlc-ai/mlc-llm/tree/main/python
Would be great to add a no_memory option to conv template. Which auto reset every time for the case of LM
the android SDK has been updated https://llm.mlc.ai/docs/deploy/android.html
closing as rest api is now part of the main
closing for now due to inactive status, we will prioritize latest models
closing for now as moss was less in a demand comparing to latest models, this issue is now inactive, feel free to open new ones.
You should be able to download the app as running on iPad
Moving to #361
Would be great if we can validate if the model lib can be reused via `vicuna-q3f16_0`, if so, we should add --reuse-lib flag or something similar so we do not...
Another item that would be relevant here for future work is to remove the name based model matching here and instead use matching of config.json, so future addition of models...