| 2025-08-18 23:36:35 - INFO - Loading model: LiquidAI/LFM2-VL-1.6B | |
| 2025-08-18 23:36:36 - INFO - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). | |
| 2025-08-18 23:36:43 - INFO - Model loaded in 7.59 seconds | |
| 2025-08-18 23:36:43 - INFO - GPU Memory Usage after model load: 3023.64 MB | |
| 2025-08-18 23:36:48 - INFO - | |
| 2025-08-18 23:36:48 - INFO - [d90238c8-2478-4c9d-bb69-a2535b9d8011] Video saved to temporary file: temp_videos/d90238c8-2478-4c9d-bb69-a2535b9d8011.mp4 | |
| 2025-08-18 23:36:48 - INFO - [d90238c8-2478-4c9d-bb69-a2535b9d8011] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-18 23:36:53 - INFO - [d90238c8-2478-4c9d-bb69-a2535b9d8011] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-18 23:36:53 - INFO - [d90238c8-2478-4c9d-bb69-a2535b9d8011] 30 frames saved to temp_videos/d90238c8-2478-4c9d-bb69-a2535b9d8011 | |
| 2025-08-18 23:36:56 - INFO - Prompt token length: 23084 | |