-
llm: Don't always evict models on CPU-only systems
发布于
2025-12-02 18:58:08 +00:00 Model eviction happens when we have at least one other model
loaded and are unable to load all layers into VRAM. However, on
CPU-only systems we can never load layers into VRAM, so this
constantly triggered eviction.Fixes #13227
下载附件