| 2025-08-21 00:29:44 - INFO - Loading model: Qwen/Qwen2-VL-2B-Instruct-AWQ | |
| 2025-08-21 00:29:48 - 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). | |
| 2025-08-21 00:30:16 - INFO - Model loaded in 32.31 seconds | |
| 2025-08-21 00:30:16 - INFO - GPU Memory Usage after model load: 2369.47 MB | |
| 2025-08-21 00:30:22 - INFO - [473c7e67-59f4-4a5d-8868-f714f9787e83] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_001.mp4' | |
| 2025-08-21 00:30:22 - INFO - [473c7e67-59f4-4a5d-8868-f714f9787e83] Video saved to temporary file: temp_videos/473c7e67-59f4-4a5d-8868-f714f9787e83.mp4 | |
| 2025-08-21 00:30:22 - INFO - [473c7e67-59f4-4a5d-8868-f714f9787e83] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:30:27 - INFO - [473c7e67-59f4-4a5d-8868-f714f9787e83] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:30:27 - INFO - [473c7e67-59f4-4a5d-8868-f714f9787e83] 30 frames saved to temp_videos/473c7e67-59f4-4a5d-8868-f714f9787e83 | |
| 2025-08-21 00:30:28 - INFO - Prompt token length: 2306 | |
| 2025-08-21 00:30:42 - INFO - Tokens per second: 15.126569543378265, Peak GPU memory MB: 4514.375 | |
| 2025-08-21 00:30:42 - INFO - [473c7e67-59f4-4a5d-8868-f714f9787e83] Inference time: 19.59 seconds, CPU usage: 28.8%, CPU core utilization: [28.0, 25.1, 38.9, 23.2] | |
| 2025-08-21 00:30:42 - INFO - [473c7e67-59f4-4a5d-8868-f714f9787e83] Cleaned up temporary frame directory: temp_videos/473c7e67-59f4-4a5d-8868-f714f9787e83 | |
| 2025-08-21 00:30:42 - INFO - [8695ced7-6ed8-4f84-8fd3-a5645e83398c] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_002.mp4' | |
| 2025-08-21 00:30:42 - INFO - [8695ced7-6ed8-4f84-8fd3-a5645e83398c] Video saved to temporary file: temp_videos/8695ced7-6ed8-4f84-8fd3-a5645e83398c.mp4 | |
| 2025-08-21 00:30:42 - INFO - [8695ced7-6ed8-4f84-8fd3-a5645e83398c] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:30:47 - INFO - [8695ced7-6ed8-4f84-8fd3-a5645e83398c] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:30:47 - INFO - [8695ced7-6ed8-4f84-8fd3-a5645e83398c] 30 frames saved to temp_videos/8695ced7-6ed8-4f84-8fd3-a5645e83398c | |
| 2025-08-21 00:30:47 - INFO - Prompt token length: 2306 | |
| 2025-08-21 00:30:58 - INFO - Tokens per second: 15.30312036179949, Peak GPU memory MB: 4514.375 | |
| 2025-08-21 00:30:58 - INFO - [8695ced7-6ed8-4f84-8fd3-a5645e83398c] Inference time: 15.90 seconds, CPU usage: 45.5%, CPU core utilization: [81.9, 29.9, 42.4, 27.9] | |
| 2025-08-21 00:30:58 - INFO - [8695ced7-6ed8-4f84-8fd3-a5645e83398c] Cleaned up temporary frame directory: temp_videos/8695ced7-6ed8-4f84-8fd3-a5645e83398c | |
| 2025-08-21 00:30:58 - INFO - [a8ea642a-4c80-4dfc-a0b6-6e9f4cf8be02] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_003.mp4' | |
| 2025-08-21 00:30:58 - INFO - [a8ea642a-4c80-4dfc-a0b6-6e9f4cf8be02] Video saved to temporary file: temp_videos/a8ea642a-4c80-4dfc-a0b6-6e9f4cf8be02.mp4 | |
| 2025-08-21 00:30:58 - INFO - [a8ea642a-4c80-4dfc-a0b6-6e9f4cf8be02] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:31:03 - INFO - [a8ea642a-4c80-4dfc-a0b6-6e9f4cf8be02] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:31:03 - INFO - [a8ea642a-4c80-4dfc-a0b6-6e9f4cf8be02] 30 frames saved to temp_videos/a8ea642a-4c80-4dfc-a0b6-6e9f4cf8be02 | |
| 2025-08-21 00:31:03 - INFO - Prompt token length: 2306 | |
| 2025-08-21 00:31:14 - INFO - Tokens per second: 15.081962195610863, Peak GPU memory MB: 4514.375 | |
| 2025-08-21 00:31:14 - INFO - [a8ea642a-4c80-4dfc-a0b6-6e9f4cf8be02] Inference time: 15.82 seconds, CPU usage: 46.3%, CPU core utilization: [66.8, 30.9, 58.6, 29.0] | |
| 2025-08-21 00:31:14 - INFO - [a8ea642a-4c80-4dfc-a0b6-6e9f4cf8be02] Cleaned up temporary frame directory: temp_videos/a8ea642a-4c80-4dfc-a0b6-6e9f4cf8be02 | |
| 2025-08-21 00:31:14 - INFO - [127051a2-002e-4513-af2a-b168f47a679c] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_004.mp4' | |
| 2025-08-21 00:31:14 - INFO - [127051a2-002e-4513-af2a-b168f47a679c] Video saved to temporary file: temp_videos/127051a2-002e-4513-af2a-b168f47a679c.mp4 | |
| 2025-08-21 00:31:14 - INFO - [127051a2-002e-4513-af2a-b168f47a679c] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:31:19 - INFO - [127051a2-002e-4513-af2a-b168f47a679c] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:31:19 - INFO - [127051a2-002e-4513-af2a-b168f47a679c] 30 frames saved to temp_videos/127051a2-002e-4513-af2a-b168f47a679c | |
| 2025-08-21 00:31:19 - INFO - Prompt token length: 2306 | |
| 2025-08-21 00:31:30 - INFO - Tokens per second: 15.1012932923201, Peak GPU memory MB: 4514.375 | |
| 2025-08-21 00:31:30 - INFO - [127051a2-002e-4513-af2a-b168f47a679c] Inference time: 15.92 seconds, CPU usage: 44.7%, CPU core utilization: [29.3, 28.1, 27.0, 94.3] | |
| 2025-08-21 00:31:30 - INFO - [127051a2-002e-4513-af2a-b168f47a679c] Cleaned up temporary frame directory: temp_videos/127051a2-002e-4513-af2a-b168f47a679c | |
| 2025-08-21 00:31:30 - INFO - [a3389ddf-4af5-4921-a824-0c0c8b4ff137] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_005.mp4' | |
| 2025-08-21 00:31:30 - INFO - [a3389ddf-4af5-4921-a824-0c0c8b4ff137] Video saved to temporary file: temp_videos/a3389ddf-4af5-4921-a824-0c0c8b4ff137.mp4 | |
| 2025-08-21 00:31:30 - INFO - [a3389ddf-4af5-4921-a824-0c0c8b4ff137] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:31:35 - INFO - [a3389ddf-4af5-4921-a824-0c0c8b4ff137] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:31:35 - INFO - [a3389ddf-4af5-4921-a824-0c0c8b4ff137] 30 frames saved to temp_videos/a3389ddf-4af5-4921-a824-0c0c8b4ff137 | |
| 2025-08-21 00:31:35 - INFO - Prompt token length: 2306 | |
| 2025-08-21 00:31:42 - INFO - Tokens per second: 14.916020163544944, Peak GPU memory MB: 4514.375 | |
| 2025-08-21 00:31:42 - INFO - [a3389ddf-4af5-4921-a824-0c0c8b4ff137] Inference time: 12.32 seconds, CPU usage: 50.3%, CPU core utilization: [37.0, 57.7, 34.8, 71.6] | |
| 2025-08-21 00:31:42 - INFO - [a3389ddf-4af5-4921-a824-0c0c8b4ff137] Cleaned up temporary frame directory: temp_videos/a3389ddf-4af5-4921-a824-0c0c8b4ff137 | |
| 2025-08-21 00:31:42 - INFO - [3a1249cb-f47c-4dab-916a-8e74dfe771cd] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_006.mp4' | |
| 2025-08-21 00:31:42 - INFO - [3a1249cb-f47c-4dab-916a-8e74dfe771cd] Video saved to temporary file: temp_videos/3a1249cb-f47c-4dab-916a-8e74dfe771cd.mp4 | |
| 2025-08-21 00:31:42 - INFO - [3a1249cb-f47c-4dab-916a-8e74dfe771cd] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:31:47 - INFO - [3a1249cb-f47c-4dab-916a-8e74dfe771cd] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:31:47 - INFO - [3a1249cb-f47c-4dab-916a-8e74dfe771cd] 30 frames saved to temp_videos/3a1249cb-f47c-4dab-916a-8e74dfe771cd | |
| 2025-08-21 00:31:47 - INFO - Prompt token length: 2306 | |
| 2025-08-21 00:31:58 - INFO - Tokens per second: 15.137056054618776, Peak GPU memory MB: 4514.375 | |
| 2025-08-21 00:31:58 - INFO - [3a1249cb-f47c-4dab-916a-8e74dfe771cd] Inference time: 16.42 seconds, CPU usage: 44.8%, CPU core utilization: [31.9, 78.8, 27.5, 41.0] | |
| 2025-08-21 00:31:58 - INFO - [3a1249cb-f47c-4dab-916a-8e74dfe771cd] Cleaned up temporary frame directory: temp_videos/3a1249cb-f47c-4dab-916a-8e74dfe771cd | |
| 2025-08-21 00:31:58 - INFO - [aeccbc49-b47d-4bb4-a28f-ce86d255d26e] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_007.mp4' | |
| 2025-08-21 00:31:58 - INFO - [aeccbc49-b47d-4bb4-a28f-ce86d255d26e] Video saved to temporary file: temp_videos/aeccbc49-b47d-4bb4-a28f-ce86d255d26e.mp4 | |
| 2025-08-21 00:31:58 - INFO - [aeccbc49-b47d-4bb4-a28f-ce86d255d26e] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:32:03 - INFO - [aeccbc49-b47d-4bb4-a28f-ce86d255d26e] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:32:03 - INFO - [aeccbc49-b47d-4bb4-a28f-ce86d255d26e] 30 frames saved to temp_videos/aeccbc49-b47d-4bb4-a28f-ce86d255d26e | |
| 2025-08-21 00:32:03 - INFO - Prompt token length: 2306 | |
| 2025-08-21 00:32:11 - INFO - Tokens per second: 15.146565978743613, Peak GPU memory MB: 4514.375 | |
| 2025-08-21 00:32:11 - INFO - [aeccbc49-b47d-4bb4-a28f-ce86d255d26e] Inference time: 12.69 seconds, CPU usage: 50.4%, CPU core utilization: [35.0, 35.3, 94.0, 37.2] | |
| 2025-08-21 00:32:11 - INFO - [aeccbc49-b47d-4bb4-a28f-ce86d255d26e] Cleaned up temporary frame directory: temp_videos/aeccbc49-b47d-4bb4-a28f-ce86d255d26e | |
| 2025-08-21 00:32:11 - INFO - [56ab2c6c-91a0-4a2b-8e6e-30b409eabd5e] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_008.mp4' | |
| 2025-08-21 00:32:11 - INFO - [56ab2c6c-91a0-4a2b-8e6e-30b409eabd5e] Video saved to temporary file: temp_videos/56ab2c6c-91a0-4a2b-8e6e-30b409eabd5e.mp4 | |
| 2025-08-21 00:32:11 - INFO - [56ab2c6c-91a0-4a2b-8e6e-30b409eabd5e] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:32:16 - INFO - [56ab2c6c-91a0-4a2b-8e6e-30b409eabd5e] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:32:16 - INFO - [56ab2c6c-91a0-4a2b-8e6e-30b409eabd5e] 30 frames saved to temp_videos/56ab2c6c-91a0-4a2b-8e6e-30b409eabd5e | |
| 2025-08-21 00:32:16 - INFO - Prompt token length: 2306 | |
| 2025-08-21 00:32:21 - INFO - Tokens per second: 15.105367104028009, Peak GPU memory MB: 4514.375 | |
| 2025-08-21 00:32:21 - INFO - [56ab2c6c-91a0-4a2b-8e6e-30b409eabd5e] Inference time: 9.88 seconds, CPU usage: 56.6%, CPU core utilization: [44.1, 58.8, 44.6, 78.6] | |
| 2025-08-21 00:32:21 - INFO - [56ab2c6c-91a0-4a2b-8e6e-30b409eabd5e] Cleaned up temporary frame directory: temp_videos/56ab2c6c-91a0-4a2b-8e6e-30b409eabd5e | |
| 2025-08-21 00:32:21 - INFO - [2b2cfccd-ea6e-47e1-a1be-cffa74ba8d17] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_009.mp4' | |
| 2025-08-21 00:32:21 - INFO - [2b2cfccd-ea6e-47e1-a1be-cffa74ba8d17] Video saved to temporary file: temp_videos/2b2cfccd-ea6e-47e1-a1be-cffa74ba8d17.mp4 | |
| 2025-08-21 00:32:21 - INFO - [2b2cfccd-ea6e-47e1-a1be-cffa74ba8d17] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:32:26 - INFO - [2b2cfccd-ea6e-47e1-a1be-cffa74ba8d17] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:32:26 - INFO - [2b2cfccd-ea6e-47e1-a1be-cffa74ba8d17] 30 frames saved to temp_videos/2b2cfccd-ea6e-47e1-a1be-cffa74ba8d17 | |
| 2025-08-21 00:32:26 - INFO - Prompt token length: 2306 | |
| 2025-08-21 00:32:31 - INFO - Tokens per second: 15.121278187118696, Peak GPU memory MB: 4514.375 | |
| 2025-08-21 00:32:31 - INFO - [2b2cfccd-ea6e-47e1-a1be-cffa74ba8d17] Inference time: 9.51 seconds, CPU usage: 57.4%, CPU core utilization: [80.4, 45.2, 47.0, 57.0] | |
| 2025-08-21 00:32:31 - INFO - [2b2cfccd-ea6e-47e1-a1be-cffa74ba8d17] Cleaned up temporary frame directory: temp_videos/2b2cfccd-ea6e-47e1-a1be-cffa74ba8d17 | |
| 2025-08-21 00:32:31 - INFO - [ccb3ba8f-6c3e-4301-884e-8a28f8f4cac3] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_010.mp4' | |
| 2025-08-21 00:32:31 - INFO - [ccb3ba8f-6c3e-4301-884e-8a28f8f4cac3] Video saved to temporary file: temp_videos/ccb3ba8f-6c3e-4301-884e-8a28f8f4cac3.mp4 | |
| 2025-08-21 00:32:31 - INFO - [ccb3ba8f-6c3e-4301-884e-8a28f8f4cac3] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:32:35 - INFO - [ccb3ba8f-6c3e-4301-884e-8a28f8f4cac3] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:32:35 - INFO - [ccb3ba8f-6c3e-4301-884e-8a28f8f4cac3] 30 frames saved to temp_videos/ccb3ba8f-6c3e-4301-884e-8a28f8f4cac3 | |
| 2025-08-21 00:32:36 - INFO - Prompt token length: 2306 | |
| 2025-08-21 00:32:54 - INFO - Tokens per second: 15.20172275516238, Peak GPU memory MB: 4514.375 | |
| 2025-08-21 00:32:54 - INFO - [ccb3ba8f-6c3e-4301-884e-8a28f8f4cac3] Inference time: 23.66 seconds, CPU usage: 39.3%, CPU core utilization: [43.6, 46.9, 30.6, 36.0] | |
| 2025-08-21 00:32:54 - INFO - [ccb3ba8f-6c3e-4301-884e-8a28f8f4cac3] Cleaned up temporary frame directory: temp_videos/ccb3ba8f-6c3e-4301-884e-8a28f8f4cac3 | |