Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`. 2025-07-10 17:14:24,734 INFO worker.py:1812 -- Started a local Ray instance. View the dashboard at http://127.0.0.1:8266  SYSTEM_PROMPT: You FIRST think about the reasoning process as an internal monologue and then provide the final answer. The reasoning process MUST BE enclosed within tags. The final answer MUST BE put in \boxed{}. 0%| | 0/3940 [00:00 131072). Running this sequence through the model will result in indexing errors (infer pid=654457) Capturing CUDA graph shapes: 0%| | 0/35 [00:00 131072). Running this sequence through the model will result in indexing errors [repeated 3x across cluster] (infer pid=654457) Capturing CUDA graph shapes: 3%|█ | 1/35 [00:00<00:17, 1.99it/s] (infer pid=654445) Capturing CUDA graph shapes: 0%| | 0/35 [00:00