Song
Song
> 在聊天窗口输入：不，再删除，黑框消失。 实测有效，太秀了！不然真的逼死强迫症
Hi guys, It seems the current prefix caching does not work on multi modal model like llava because the hash of block only takes previous token ids and the image...
I'm not working on it. Really appreciate it! And if anything comes up, just let us know.
I'm not working on it. Really appreciate it! And if anything comes up, just let us know.
> Hi,I'm integrating Step-Audio2 following the Qwen3-Omni pattern, but its TTS component depends on cosyvoice and flashcosyvoice. I'm not sure which approach is better: integrating the CosyVoice series first, or...