Files
koboldcpp/tools
Ed Addario 0596704284 quant : Optimise memory usage by evicting weights after processing each layer (#22877)
* Evict weights from memory after processing each layer

* Revert changes

* Move unmap to libllama

* Unmap weights offloaded to backend

* Change member's constness

* Remove unmap weights offloaded to backend
2026-08-18 16:22:32 +02:00
..
2026-08-11 14:18:30 +02:00