| 2025-08-18 22:13:56 - INFO - Loading model: Qwen/Qwen2-VL-2B-Instruct-AWQ | |
| 2025-08-18 22:13:58 - 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 22:14:05 - INFO - Model loaded in 8.85 seconds | |
| 2025-08-18 22:14:05 - INFO - GPU Memory Usage after model load: 2.31 GB | |
| 2025-08-18 22:14:11 - INFO - [723f6887-db9b-43c9-846f-fc1b2cb67237] Received new video inference request. Prompt: 'Please describe the video in detail.', Video: 'messi_part_001.mp4' | |
| 2025-08-18 22:14:11 - INFO - [723f6887-db9b-43c9-846f-fc1b2cb67237] Video saved to temporary file: temp_videos/723f6887-db9b-43c9-846f-fc1b2cb67237.mp4 | |
| 2025-08-18 22:14:11 - INFO - [723f6887-db9b-43c9-846f-fc1b2cb67237] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-18 22:14:13 - INFO - [723f6887-db9b-43c9-846f-fc1b2cb67237] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-18 22:14:13 - INFO - [723f6887-db9b-43c9-846f-fc1b2cb67237] 30 frames saved to temp_videos/723f6887-db9b-43c9-846f-fc1b2cb67237 | |
| 2025-08-18 22:14:14 - INFO - Prompt token length: 2278 | |
| 2025-08-18 22:14:34 - INFO - Tokens per second: 12.449120956672985, Avg GPU memory MB: 3164.236328125 | |
| 2025-08-18 22:14:34 - INFO - [723f6887-db9b-43c9-846f-fc1b2cb67237] Cleaned up temporary file: temp_videos/723f6887-db9b-43c9-846f-fc1b2cb67237.mp4 | |
| 2025-08-18 22:14:34 - INFO - [723f6887-db9b-43c9-846f-fc1b2cb67237] Cleaned up temporary frame directory: temp_videos/723f6887-db9b-43c9-846f-fc1b2cb67237 | |
| 2025-08-18 22:15:33 - INFO - [3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e] Received new video inference request. Prompt: 'Please describe the video.', Video: 'messi_part_001.mp4' | |
| 2025-08-18 22:15:33 - INFO - [3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e] Video saved to temporary file: temp_videos/3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e.mp4 | |
| 2025-08-18 22:15:33 - INFO - [3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-18 22:15:35 - INFO - [3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-18 22:15:35 - INFO - [3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e] 30 frames saved to temp_videos/3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e | |
| 2025-08-18 22:15:36 - INFO - Prompt token length: 2276 | |
| 2025-08-18 22:15:44 - INFO - Tokens per second: 11.375589334843664, Avg GPU memory MB: 3163.87451171875 | |
| 2025-08-18 22:15:44 - INFO - [3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e] Cleaned up temporary file: temp_videos/3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e.mp4 | |
| 2025-08-18 22:15:44 - INFO - [3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e] Cleaned up temporary frame directory: temp_videos/3a6ec3f7-fcb1-4c31-ab9f-9aed3009645e | |