mit-han-lab / TinyChatEngine

TinyChatEngine: On-Device LLM Inference Library
https://mit-han-lab.github.io/TinyChatEngine/
MIT License
624 stars 58 forks source link

Quality of life fixes for GPU users and future development #79

Closed Jiminator closed 7 months ago

Jiminator commented 7 months ago

Description

This PR fixed an issue where edge GPU users couldn't run the voicechat as the changes were previously only in the .cc files and not the .cu files. Also merged voice chat code into chat so that now changes the chat application do not have to be duplicated in voicechat file.

Changes Made

Checklist

Please review and check off these items before submitting your pull request: