Rattus 65994f4ea4 qwen: reduce VRAM usage
Clean up a bunch of stacked and no-longer-needed tensors on the QWEN
VRAM peak (currently FFN).

With this I go from OOMing at B=37x1328x1328 to being able to
succesfully run B=47 (RTX5090).
2025-11-12 22:27:13 +10:00
..
2025-10-05 15:41:19 -04:00
2025-11-12 22:27:13 +10:00
2025-04-14 18:00:33 -04:00