baronrabban 4c7249e98d Fix draft model ignoring draft_gpu_split on load ...

The exllamav3 backend parses the user-configured draft_gpu_split into
self.draft_gpu_split, but load_model_sync passed self.gpu_split (the main
model's split) when loading the draft model, so the draft split was
silently ignored. Use self.draft_gpu_split instead.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-10 18:45:52 -04:00

..

exllamav2

…

exllamav3

Fix draft model ignoring draft_gpu_split on load

2026-06-10 18:45:52 -04:00

infinity

…

base_model_container.py

…