Kawrakow 86f4f516e5
Auto-fit offloaded tensors to available VRAM (MoE models) (#1501)
* WIP: automatically fit model in available VRAM

* WIP

* This seems pretty solid
2026-03-25 07:29:29 +01:00
..
2024-07-27 07:55:01 +02:00
2025-12-15 08:27:20 +01:00
2023-11-13 14:16:23 +02:00