centersl/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-03-28 03:08:44 +07:00
Code Issues Packages Projects Releases Wiki Activity
Files
parth/decrease-concurrent-download-hf
ollama/llm/server_test.go
Jesse Gross 5317202c38 llm: Don't always evict models on CPU-only systems 
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
2025-12-02 10:58:08 -08:00

12 KiB
Raw Permalink Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink