| 2025-08-19 01:03:10 - INFO - Loading model: google/gemma-3-4b-it | |
| 2025-08-19 01:03:11 - 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). | |
| 2025-08-19 01:03:37 - INFO - Model loaded in 26.97 seconds | |
| 2025-08-19 01:03:37 - INFO - GPU Memory Usage after model load: 8201.85 MB | |
| 2025-08-19 01:03:58 - INFO - [ddbb264c-a911-43d4-aee3-8aebd82a1e83] Received new video inference request. Prompt: 'Please describe the video.', Video: 'messi_part_001.mp4' | |
| 2025-08-19 01:03:58 - INFO - [ddbb264c-a911-43d4-aee3-8aebd82a1e83] Video saved to temporary file: temp_videos/ddbb264c-a911-43d4-aee3-8aebd82a1e83.mp4 | |
| 2025-08-19 01:03:58 - INFO - [ddbb264c-a911-43d4-aee3-8aebd82a1e83] Extracting frames using method: uniform, rate/threshold: 5 | |
| 2025-08-19 01:03:58 - INFO - [ddbb264c-a911-43d4-aee3-8aebd82a1e83] Extracted 5 frames successfully. Saving to temporary files... | |
| 2025-08-19 01:03:58 - INFO - [ddbb264c-a911-43d4-aee3-8aebd82a1e83] 5 frames saved to temp_videos/ddbb264c-a911-43d4-aee3-8aebd82a1e83 | |
| 2025-08-19 01:03:58 - INFO - Prompt token length: 1317 | |