mrleo1nid/gpu-rent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
97 Commits 1 Branch 0 Tags
1d431e3a05b94c66e2984ed42ae349e3dca60957
Commit Graph
2 Commits
Author SHA1 Message Date
Leonid PershinandCursor 789fa26918 Pick cheapest GPU SKU and pin the VM to an existing disk AZ. 
Scan ru-6 by Nova availability zones (a/b/c). First boot uses FLAVOR_SIZE_PRESET=cheap; reruns stay on the disk segment.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-22 00:06:44 +03:00
Leonid PershinandCursor 5d0c30f66b Enhance Ollama integration and model management 
- Implemented support for parallel embedding in Ollama, allowing for improved performance in chat and memory functions.
- Updated the `ollama-roles.json` and CPU Modelfile to accommodate new features.
- Increased the maximum loaded models and parallel processing limits to 2, optimizing resource usage.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-21 23:05:48 +03:00