mirror of
https://github.com/vladmandic/automatic
synced 2026-09-11 23:56:44 +02:00
CalamitousFelicitousness
a51e1501d6
- Initialize KV caches before moving model to device - Disable flex_attention decoding to avoid torch.compile hang - Remove unused compile step (controlled by cuda_compile setting) The flex_attention's create_block_mask triggers torch compilation which can hang the system when called during model preload.