Commits · 369eda65f53af3ea38e4e9a80be7d7ec5baa5c1c · OpenDAS / ollama

11 Mar, 2024 1 commit
- update llama.cpp submodule to `ceca1ae` (#3064) · 369eda65
  Jeffrey Morgan authored Mar 11, 2024
  
  369eda65
09 Mar, 2024 1 commit
- update llama.cpp submodule to `77d1ac7` (#3030) · 1ffb1e28
  Jeffrey Morgan authored Mar 09, 2024
  
  1ffb1e28
08 Mar, 2024 1 commit
- update llama.cpp submodule to `6cdabe6` (#2999) · 0e4669b0
  Jeffrey Morgan authored Mar 08, 2024
  
  0e4669b0
01 Mar, 2024 1 commit
- update llama.cpp submodule to `c29af7e` (#2868) · 21347e1e
  Jeffrey Morgan authored Mar 01, 2024
  
  21347e1e
20 Feb, 2024 1 commit
- update llama.cpp submodule to `66c1968f7` (#2618) · 4613a080
  Jeffrey Morgan authored Feb 20, 2024
  
  4613a080
19 Feb, 2024 1 commit

Daniel Hiltgen authored Feb 18, 2024

This should resolve the problem where we don't fully unload from the GPU
when we go idle.

fc39a6cd