Closed
Description
🚀 The feature, motivation and pitch
I notice in #12642, we disable prefix caching when model is with mla (deepseek). Is there any problem of mla coming with prefix caching? If we can enable it by any chance?
Alternatives
No response
Additional context
No response
Before submitting a new issue...
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.