abetlen / abetlen/llama-cpp-python

[FR] Auto-load/unload models to save memory when unused

未關閉
#736 0 則留言 20 個 reaction 已指派 0 人 在 GitHub 檢視
enhancement server
主要語言
Python
星號
10.6k
分支
1.4k
PR 合併指標
PR 指標待擷取

描述

**Is your feature request related to a problem? Please describe.**
In a shared machine, or even a personal one, it's better to automatically free up the memory used when the model is not in use.

**Describe the solution you'd like**
Some `idle_before_unload=600` parameter that unloads the model after that many seconds of being idle. The model should be reloaded automatically whenever it is used again.

**Additional context**
- https://github.com/abetlen/llama-cpp-python/issues/302

貢獻指南

開啟貢獻指南

評估

這個 Issue 還沒有評估資料。

把新 issue 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。