| 2025-08-20 23:34:55 - INFO - Loading model: openbmb/MiniCPM-V-4 | |
| 2025-08-20 23:34:56 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:36:01 - INFO - Model loaded in 65.64 seconds | |
| 2025-08-20 23:36:01 - INFO - GPU Memory Usage after model load: 7802.99 MB | |
| 2025-08-20 23:36:30 - INFO - [5373d18b-66ad-4a38-b02b-dbac9e400b89] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_001.mp4' | |
| 2025-08-20 23:36:30 - INFO - [5373d18b-66ad-4a38-b02b-dbac9e400b89] Video saved to temporary file: temp_videos/5373d18b-66ad-4a38-b02b-dbac9e400b89.mp4 | |
| 2025-08-20 23:36:30 - INFO - [5373d18b-66ad-4a38-b02b-dbac9e400b89] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:36:36 - INFO - [5373d18b-66ad-4a38-b02b-dbac9e400b89] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:36:36 - INFO - [5373d18b-66ad-4a38-b02b-dbac9e400b89] 30 frames saved to temp_videos/5373d18b-66ad-4a38-b02b-dbac9e400b89 | |
| 2025-08-20 23:36:53 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:37:12 - INFO - Tokens per second: 8.779788779248046, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:37:12 - INFO - [5373d18b-66ad-4a38-b02b-dbac9e400b89] Inference time: 41.20 seconds, CPU usage: 20.4%, CPU core utilization: [14.8, 25.6, 19.6, 21.6] | |
| 2025-08-20 23:37:12 - INFO - [5373d18b-66ad-4a38-b02b-dbac9e400b89] Cleaned up temporary frame directory: temp_videos/5373d18b-66ad-4a38-b02b-dbac9e400b89 | |
| 2025-08-20 23:37:12 - INFO - [cbcd04dd-9447-4344-812e-e4387f036fea] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_002.mp4' | |
| 2025-08-20 23:37:12 - INFO - [cbcd04dd-9447-4344-812e-e4387f036fea] Video saved to temporary file: temp_videos/cbcd04dd-9447-4344-812e-e4387f036fea.mp4 | |
| 2025-08-20 23:37:12 - INFO - [cbcd04dd-9447-4344-812e-e4387f036fea] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:37:17 - INFO - [cbcd04dd-9447-4344-812e-e4387f036fea] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:37:17 - INFO - [cbcd04dd-9447-4344-812e-e4387f036fea] 30 frames saved to temp_videos/cbcd04dd-9447-4344-812e-e4387f036fea | |
| 2025-08-20 23:37:29 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:37:45 - INFO - Tokens per second: 8.238054802466655, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:37:45 - INFO - [cbcd04dd-9447-4344-812e-e4387f036fea] Inference time: 33.71 seconds, CPU usage: 35.8%, CPU core utilization: [31.6, 59.3, 28.2, 24.1] | |
| 2025-08-20 23:37:45 - INFO - [cbcd04dd-9447-4344-812e-e4387f036fea] Cleaned up temporary frame directory: temp_videos/cbcd04dd-9447-4344-812e-e4387f036fea | |
| 2025-08-20 23:37:45 - INFO - [4ca8090e-ea72-431d-aa92-756575a05665] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_003.mp4' | |
| 2025-08-20 23:37:45 - INFO - [4ca8090e-ea72-431d-aa92-756575a05665] Video saved to temporary file: temp_videos/4ca8090e-ea72-431d-aa92-756575a05665.mp4 | |
| 2025-08-20 23:37:45 - INFO - [4ca8090e-ea72-431d-aa92-756575a05665] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:37:50 - INFO - [4ca8090e-ea72-431d-aa92-756575a05665] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:37:50 - INFO - [4ca8090e-ea72-431d-aa92-756575a05665] 30 frames saved to temp_videos/4ca8090e-ea72-431d-aa92-756575a05665 | |
| 2025-08-20 23:38:03 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:38:26 - INFO - Tokens per second: 9.842206491452542, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:38:26 - INFO - [4ca8090e-ea72-431d-aa92-756575a05665] Inference time: 40.18 seconds, CPU usage: 34.2%, CPU core utilization: [42.5, 14.8, 64.8, 14.6] | |
| 2025-08-20 23:38:26 - INFO - [4ca8090e-ea72-431d-aa92-756575a05665] Cleaned up temporary frame directory: temp_videos/4ca8090e-ea72-431d-aa92-756575a05665 | |
| 2025-08-20 23:38:26 - INFO - [e7c9965e-02c8-4472-bc73-adb425fc488d] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_004.mp4' | |
| 2025-08-20 23:38:26 - INFO - [e7c9965e-02c8-4472-bc73-adb425fc488d] Video saved to temporary file: temp_videos/e7c9965e-02c8-4472-bc73-adb425fc488d.mp4 | |
| 2025-08-20 23:38:26 - INFO - [e7c9965e-02c8-4472-bc73-adb425fc488d] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:38:30 - INFO - [e7c9965e-02c8-4472-bc73-adb425fc488d] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:38:30 - INFO - [e7c9965e-02c8-4472-bc73-adb425fc488d] 30 frames saved to temp_videos/e7c9965e-02c8-4472-bc73-adb425fc488d | |
| 2025-08-20 23:38:43 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:38:57 - INFO - Tokens per second: 7.223886604016651, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:38:57 - INFO - [e7c9965e-02c8-4472-bc73-adb425fc488d] Inference time: 31.57 seconds, CPU usage: 36.1%, CPU core utilization: [35.9, 19.2, 72.5, 16.5] | |
| 2025-08-20 23:38:57 - INFO - [e7c9965e-02c8-4472-bc73-adb425fc488d] Cleaned up temporary frame directory: temp_videos/e7c9965e-02c8-4472-bc73-adb425fc488d | |
| 2025-08-20 23:38:57 - INFO - [42ed726f-5d5b-4a66-bebd-387f3916eea3] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_005.mp4' | |
| 2025-08-20 23:38:57 - INFO - [42ed726f-5d5b-4a66-bebd-387f3916eea3] Video saved to temporary file: temp_videos/42ed726f-5d5b-4a66-bebd-387f3916eea3.mp4 | |
| 2025-08-20 23:38:57 - INFO - [42ed726f-5d5b-4a66-bebd-387f3916eea3] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:39:02 - INFO - [42ed726f-5d5b-4a66-bebd-387f3916eea3] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:39:02 - INFO - [42ed726f-5d5b-4a66-bebd-387f3916eea3] 30 frames saved to temp_videos/42ed726f-5d5b-4a66-bebd-387f3916eea3 | |
| 2025-08-20 23:39:15 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:39:35 - INFO - Tokens per second: 9.414676082668533, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:39:35 - INFO - [42ed726f-5d5b-4a66-bebd-387f3916eea3] Inference time: 38.23 seconds, CPU usage: 34.6%, CPU core utilization: [34.4, 30.3, 14.1, 59.5] | |
| 2025-08-20 23:39:35 - INFO - [42ed726f-5d5b-4a66-bebd-387f3916eea3] Cleaned up temporary frame directory: temp_videos/42ed726f-5d5b-4a66-bebd-387f3916eea3 | |
| 2025-08-20 23:39:35 - INFO - [770b60c1-2ad5-4fc8-a042-36f7397d63c8] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_006.mp4' | |
| 2025-08-20 23:39:35 - INFO - [770b60c1-2ad5-4fc8-a042-36f7397d63c8] Video saved to temporary file: temp_videos/770b60c1-2ad5-4fc8-a042-36f7397d63c8.mp4 | |
| 2025-08-20 23:39:35 - INFO - [770b60c1-2ad5-4fc8-a042-36f7397d63c8] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:39:40 - INFO - [770b60c1-2ad5-4fc8-a042-36f7397d63c8] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:39:40 - INFO - [770b60c1-2ad5-4fc8-a042-36f7397d63c8] 30 frames saved to temp_videos/770b60c1-2ad5-4fc8-a042-36f7397d63c8 | |
| 2025-08-20 23:39:53 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:40:12 - INFO - Tokens per second: 9.018116223758131, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:40:12 - INFO - [770b60c1-2ad5-4fc8-a042-36f7397d63c8] Inference time: 36.60 seconds, CPU usage: 35.1%, CPU core utilization: [47.3, 19.3, 54.1, 19.6] | |
| 2025-08-20 23:40:12 - INFO - [770b60c1-2ad5-4fc8-a042-36f7397d63c8] Cleaned up temporary frame directory: temp_videos/770b60c1-2ad5-4fc8-a042-36f7397d63c8 | |
| 2025-08-20 23:40:12 - INFO - [979c0d57-545b-43cd-8601-b2ae280d1197] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_007.mp4' | |
| 2025-08-20 23:40:12 - INFO - [979c0d57-545b-43cd-8601-b2ae280d1197] Video saved to temporary file: temp_videos/979c0d57-545b-43cd-8601-b2ae280d1197.mp4 | |
| 2025-08-20 23:40:12 - INFO - [979c0d57-545b-43cd-8601-b2ae280d1197] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:40:17 - INFO - [979c0d57-545b-43cd-8601-b2ae280d1197] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:40:17 - INFO - [979c0d57-545b-43cd-8601-b2ae280d1197] 30 frames saved to temp_videos/979c0d57-545b-43cd-8601-b2ae280d1197 | |
| 2025-08-20 23:40:30 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:40:46 - INFO - Tokens per second: 8.128884269772154, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:40:46 - INFO - [979c0d57-545b-43cd-8601-b2ae280d1197] Inference time: 33.74 seconds, CPU usage: 35.5%, CPU core utilization: [29.4, 48.5, 49.0, 15.1] | |
| 2025-08-20 23:40:46 - INFO - [979c0d57-545b-43cd-8601-b2ae280d1197] Cleaned up temporary frame directory: temp_videos/979c0d57-545b-43cd-8601-b2ae280d1197 | |
| 2025-08-20 23:40:46 - INFO - [09341564-481c-4f01-b9ae-fd64f197af41] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_008.mp4' | |
| 2025-08-20 23:40:46 - INFO - [09341564-481c-4f01-b9ae-fd64f197af41] Video saved to temporary file: temp_videos/09341564-481c-4f01-b9ae-fd64f197af41.mp4 | |
| 2025-08-20 23:40:46 - INFO - [09341564-481c-4f01-b9ae-fd64f197af41] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:40:51 - INFO - [09341564-481c-4f01-b9ae-fd64f197af41] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:40:51 - INFO - [09341564-481c-4f01-b9ae-fd64f197af41] 30 frames saved to temp_videos/09341564-481c-4f01-b9ae-fd64f197af41 | |
| 2025-08-20 23:41:04 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:41:20 - INFO - Tokens per second: 8.104748907769563, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:41:20 - INFO - [09341564-481c-4f01-b9ae-fd64f197af41] Inference time: 33.69 seconds, CPU usage: 35.7%, CPU core utilization: [22.5, 24.9, 45.2, 50.3] | |
| 2025-08-20 23:41:20 - INFO - [09341564-481c-4f01-b9ae-fd64f197af41] Cleaned up temporary frame directory: temp_videos/09341564-481c-4f01-b9ae-fd64f197af41 | |
| 2025-08-20 23:41:20 - INFO - [152baa13-549f-4cd5-a9fd-b9caa193427c] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_009.mp4' | |
| 2025-08-20 23:41:20 - INFO - [152baa13-549f-4cd5-a9fd-b9caa193427c] Video saved to temporary file: temp_videos/152baa13-549f-4cd5-a9fd-b9caa193427c.mp4 | |
| 2025-08-20 23:41:20 - INFO - [152baa13-549f-4cd5-a9fd-b9caa193427c] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:41:24 - INFO - [152baa13-549f-4cd5-a9fd-b9caa193427c] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:41:24 - INFO - [152baa13-549f-4cd5-a9fd-b9caa193427c] 30 frames saved to temp_videos/152baa13-549f-4cd5-a9fd-b9caa193427c | |
| 2025-08-20 23:41:37 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:41:54 - INFO - Tokens per second: 8.260490846413186, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:41:54 - INFO - [152baa13-549f-4cd5-a9fd-b9caa193427c] Inference time: 34.09 seconds, CPU usage: 35.2%, CPU core utilization: [44.4, 20.5, 41.4, 34.6] | |
| 2025-08-20 23:41:54 - INFO - [152baa13-549f-4cd5-a9fd-b9caa193427c] Cleaned up temporary frame directory: temp_videos/152baa13-549f-4cd5-a9fd-b9caa193427c | |
| 2025-08-20 23:41:54 - INFO - [f16dda49-2af2-4b53-b80c-e152a2424314] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_010.mp4' | |
| 2025-08-20 23:41:54 - INFO - [f16dda49-2af2-4b53-b80c-e152a2424314] Video saved to temporary file: temp_videos/f16dda49-2af2-4b53-b80c-e152a2424314.mp4 | |
| 2025-08-20 23:41:54 - INFO - [f16dda49-2af2-4b53-b80c-e152a2424314] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:41:58 - INFO - [f16dda49-2af2-4b53-b80c-e152a2424314] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:41:58 - INFO - [f16dda49-2af2-4b53-b80c-e152a2424314] 30 frames saved to temp_videos/f16dda49-2af2-4b53-b80c-e152a2424314 | |
| 2025-08-20 23:42:11 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:42:28 - INFO - Tokens per second: 8.474433175082025, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:42:28 - INFO - [f16dda49-2af2-4b53-b80c-e152a2424314] Inference time: 34.75 seconds, CPU usage: 35.3%, CPU core utilization: [40.2, 15.6, 70.7, 14.8] | |
| 2025-08-20 23:42:28 - INFO - [f16dda49-2af2-4b53-b80c-e152a2424314] Cleaned up temporary frame directory: temp_videos/f16dda49-2af2-4b53-b80c-e152a2424314 | |
| 2025-08-20 23:42:28 - INFO - [4ad4941a-d5b6-4fef-bf4e-4ba8bf29ac55] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_011.mp4' | |
| 2025-08-20 23:42:28 - INFO - [4ad4941a-d5b6-4fef-bf4e-4ba8bf29ac55] Video saved to temporary file: temp_videos/4ad4941a-d5b6-4fef-bf4e-4ba8bf29ac55.mp4 | |
| 2025-08-20 23:42:28 - INFO - [4ad4941a-d5b6-4fef-bf4e-4ba8bf29ac55] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:42:33 - INFO - [4ad4941a-d5b6-4fef-bf4e-4ba8bf29ac55] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:42:33 - INFO - [4ad4941a-d5b6-4fef-bf4e-4ba8bf29ac55] 30 frames saved to temp_videos/4ad4941a-d5b6-4fef-bf4e-4ba8bf29ac55 | |
| 2025-08-20 23:42:46 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:43:00 - INFO - Tokens per second: 7.281456041328239, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:43:00 - INFO - [4ad4941a-d5b6-4fef-bf4e-4ba8bf29ac55] Inference time: 31.78 seconds, CPU usage: 35.9%, CPU core utilization: [41.3, 59.3, 27.5, 15.5] | |
| 2025-08-20 23:43:00 - INFO - [4ad4941a-d5b6-4fef-bf4e-4ba8bf29ac55] Cleaned up temporary frame directory: temp_videos/4ad4941a-d5b6-4fef-bf4e-4ba8bf29ac55 | |
| 2025-08-20 23:43:00 - INFO - [b91fc444-5706-4fc6-b7e3-97045044f1ad] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_012.mp4' | |
| 2025-08-20 23:43:00 - INFO - [b91fc444-5706-4fc6-b7e3-97045044f1ad] Video saved to temporary file: temp_videos/b91fc444-5706-4fc6-b7e3-97045044f1ad.mp4 | |
| 2025-08-20 23:43:00 - INFO - [b91fc444-5706-4fc6-b7e3-97045044f1ad] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:43:05 - INFO - [b91fc444-5706-4fc6-b7e3-97045044f1ad] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:43:05 - INFO - [b91fc444-5706-4fc6-b7e3-97045044f1ad] 30 frames saved to temp_videos/b91fc444-5706-4fc6-b7e3-97045044f1ad | |
| 2025-08-20 23:43:18 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:43:34 - INFO - Tokens per second: 8.229193657182282, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:43:34 - INFO - [b91fc444-5706-4fc6-b7e3-97045044f1ad] Inference time: 34.07 seconds, CPU usage: 35.4%, CPU core utilization: [17.3, 58.4, 14.4, 51.7] | |
| 2025-08-20 23:43:34 - INFO - [b91fc444-5706-4fc6-b7e3-97045044f1ad] Cleaned up temporary frame directory: temp_videos/b91fc444-5706-4fc6-b7e3-97045044f1ad | |
| 2025-08-20 23:43:34 - INFO - [8470205f-d443-4e1d-9371-99a2ab5f76b6] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_013.mp4' | |
| 2025-08-20 23:43:34 - INFO - [8470205f-d443-4e1d-9371-99a2ab5f76b6] Video saved to temporary file: temp_videos/8470205f-d443-4e1d-9371-99a2ab5f76b6.mp4 | |
| 2025-08-20 23:43:34 - INFO - [8470205f-d443-4e1d-9371-99a2ab5f76b6] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:43:39 - INFO - [8470205f-d443-4e1d-9371-99a2ab5f76b6] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:43:39 - INFO - [8470205f-d443-4e1d-9371-99a2ab5f76b6] 30 frames saved to temp_videos/8470205f-d443-4e1d-9371-99a2ab5f76b6 | |
| 2025-08-20 23:43:52 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:44:08 - INFO - Tokens per second: 7.933309315527597, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:44:08 - INFO - [8470205f-d443-4e1d-9371-99a2ab5f76b6] Inference time: 33.32 seconds, CPU usage: 35.5%, CPU core utilization: [59.0, 27.1, 15.4, 40.4] | |
| 2025-08-20 23:44:08 - INFO - [8470205f-d443-4e1d-9371-99a2ab5f76b6] Cleaned up temporary frame directory: temp_videos/8470205f-d443-4e1d-9371-99a2ab5f76b6 | |
| 2025-08-20 23:44:08 - INFO - [87989d50-7108-4eea-a2e2-3ac68ce850b0] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_014.mp4' | |
| 2025-08-20 23:44:08 - INFO - [87989d50-7108-4eea-a2e2-3ac68ce850b0] Video saved to temporary file: temp_videos/87989d50-7108-4eea-a2e2-3ac68ce850b0.mp4 | |
| 2025-08-20 23:44:08 - INFO - [87989d50-7108-4eea-a2e2-3ac68ce850b0] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:44:13 - INFO - [87989d50-7108-4eea-a2e2-3ac68ce850b0] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:44:13 - INFO - [87989d50-7108-4eea-a2e2-3ac68ce850b0] 30 frames saved to temp_videos/87989d50-7108-4eea-a2e2-3ac68ce850b0 | |
| 2025-08-20 23:44:25 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:44:47 - INFO - Tokens per second: 9.6318698479325, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:44:47 - INFO - [87989d50-7108-4eea-a2e2-3ac68ce850b0] Inference time: 39.46 seconds, CPU usage: 34.5%, CPU core utilization: [46.5, 21.2, 28.6, 41.7] | |
| 2025-08-20 23:44:47 - INFO - [87989d50-7108-4eea-a2e2-3ac68ce850b0] Cleaned up temporary frame directory: temp_videos/87989d50-7108-4eea-a2e2-3ac68ce850b0 | |
| 2025-08-20 23:44:47 - INFO - [2e1a26e8-2e97-4635-9479-94580fac857d] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_015.mp4' | |
| 2025-08-20 23:44:47 - INFO - [2e1a26e8-2e97-4635-9479-94580fac857d] Video saved to temporary file: temp_videos/2e1a26e8-2e97-4635-9479-94580fac857d.mp4 | |
| 2025-08-20 23:44:47 - INFO - [2e1a26e8-2e97-4635-9479-94580fac857d] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:44:52 - INFO - [2e1a26e8-2e97-4635-9479-94580fac857d] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:44:52 - INFO - [2e1a26e8-2e97-4635-9479-94580fac857d] 30 frames saved to temp_videos/2e1a26e8-2e97-4635-9479-94580fac857d | |
| 2025-08-20 23:45:05 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:45:19 - INFO - Tokens per second: 7.41501152980709, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:45:19 - INFO - [2e1a26e8-2e97-4635-9479-94580fac857d] Inference time: 32.04 seconds, CPU usage: 35.9%, CPU core utilization: [44.7, 31.3, 28.4, 39.1] | |
| 2025-08-20 23:45:19 - INFO - [2e1a26e8-2e97-4635-9479-94580fac857d] Cleaned up temporary frame directory: temp_videos/2e1a26e8-2e97-4635-9479-94580fac857d | |
| 2025-08-20 23:45:19 - INFO - [e846a73a-a898-4957-8799-5b00b759bd1c] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_016.mp4' | |
| 2025-08-20 23:45:19 - INFO - [e846a73a-a898-4957-8799-5b00b759bd1c] Video saved to temporary file: temp_videos/e846a73a-a898-4957-8799-5b00b759bd1c.mp4 | |
| 2025-08-20 23:45:19 - INFO - [e846a73a-a898-4957-8799-5b00b759bd1c] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:45:24 - INFO - [e846a73a-a898-4957-8799-5b00b759bd1c] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:45:24 - INFO - [e846a73a-a898-4957-8799-5b00b759bd1c] 30 frames saved to temp_videos/e846a73a-a898-4957-8799-5b00b759bd1c | |
| 2025-08-20 23:45:37 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:45:57 - INFO - Tokens per second: 9.31005578568323, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:45:57 - INFO - [e846a73a-a898-4957-8799-5b00b759bd1c] Inference time: 37.84 seconds, CPU usage: 34.4%, CPU core utilization: [26.5, 43.5, 51.5, 16.2] | |
| 2025-08-20 23:45:57 - INFO - [e846a73a-a898-4957-8799-5b00b759bd1c] Cleaned up temporary frame directory: temp_videos/e846a73a-a898-4957-8799-5b00b759bd1c | |
| 2025-08-20 23:45:57 - INFO - [e95f483f-4174-421b-b85c-177358e58486] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_017.mp4' | |
| 2025-08-20 23:45:57 - INFO - [e95f483f-4174-421b-b85c-177358e58486] Video saved to temporary file: temp_videos/e95f483f-4174-421b-b85c-177358e58486.mp4 | |
| 2025-08-20 23:45:57 - INFO - [e95f483f-4174-421b-b85c-177358e58486] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:46:02 - INFO - [e95f483f-4174-421b-b85c-177358e58486] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:46:02 - INFO - [e95f483f-4174-421b-b85c-177358e58486] 30 frames saved to temp_videos/e95f483f-4174-421b-b85c-177358e58486 | |
| 2025-08-20 23:46:15 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:46:29 - INFO - Tokens per second: 7.603712717977961, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:46:29 - INFO - [e95f483f-4174-421b-b85c-177358e58486] Inference time: 32.46 seconds, CPU usage: 36.2%, CPU core utilization: [34.5, 20.6, 74.3, 15.2] | |
| 2025-08-20 23:46:29 - INFO - [e95f483f-4174-421b-b85c-177358e58486] Cleaned up temporary frame directory: temp_videos/e95f483f-4174-421b-b85c-177358e58486 | |
| 2025-08-20 23:46:29 - INFO - [0fae1f1a-6dfb-4b0e-aaa9-b36a4e6ab08b] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_018.mp4' | |
| 2025-08-20 23:46:29 - INFO - [0fae1f1a-6dfb-4b0e-aaa9-b36a4e6ab08b] Video saved to temporary file: temp_videos/0fae1f1a-6dfb-4b0e-aaa9-b36a4e6ab08b.mp4 | |
| 2025-08-20 23:46:29 - INFO - [0fae1f1a-6dfb-4b0e-aaa9-b36a4e6ab08b] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:46:37 - INFO - [0fae1f1a-6dfb-4b0e-aaa9-b36a4e6ab08b] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:46:37 - INFO - [0fae1f1a-6dfb-4b0e-aaa9-b36a4e6ab08b] 30 frames saved to temp_videos/0fae1f1a-6dfb-4b0e-aaa9-b36a4e6ab08b | |
| 2025-08-20 23:46:50 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:47:11 - INFO - Tokens per second: 9.605931622305029, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:47:11 - INFO - [0fae1f1a-6dfb-4b0e-aaa9-b36a4e6ab08b] Inference time: 41.81 seconds, CPU usage: 53.0%, CPU core utilization: [47.2, 51.0, 44.8, 69.2] | |
| 2025-08-20 23:47:11 - INFO - [0fae1f1a-6dfb-4b0e-aaa9-b36a4e6ab08b] Cleaned up temporary frame directory: temp_videos/0fae1f1a-6dfb-4b0e-aaa9-b36a4e6ab08b | |
| 2025-08-20 23:47:11 - INFO - [1317b652-49c6-45bf-bbb5-329fa9fd9572] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_019.mp4' | |
| 2025-08-20 23:47:11 - INFO - [1317b652-49c6-45bf-bbb5-329fa9fd9572] Video saved to temporary file: temp_videos/1317b652-49c6-45bf-bbb5-329fa9fd9572.mp4 | |
| 2025-08-20 23:47:11 - INFO - [1317b652-49c6-45bf-bbb5-329fa9fd9572] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:47:16 - INFO - [1317b652-49c6-45bf-bbb5-329fa9fd9572] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:47:16 - INFO - [1317b652-49c6-45bf-bbb5-329fa9fd9572] 30 frames saved to temp_videos/1317b652-49c6-45bf-bbb5-329fa9fd9572 | |
| 2025-08-20 23:47:29 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:47:42 - INFO - Tokens per second: 6.553943613195835, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:47:42 - INFO - [1317b652-49c6-45bf-bbb5-329fa9fd9572] Inference time: 30.42 seconds, CPU usage: 36.3%, CPU core utilization: [28.7, 56.6, 44.1, 15.8] | |
| 2025-08-20 23:47:42 - INFO - [1317b652-49c6-45bf-bbb5-329fa9fd9572] Cleaned up temporary frame directory: temp_videos/1317b652-49c6-45bf-bbb5-329fa9fd9572 | |
| 2025-08-20 23:47:42 - INFO - [dc27d7c0-3dad-49d5-aa0b-79cc072fe0ef] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_020.mp4' | |
| 2025-08-20 23:47:42 - INFO - [dc27d7c0-3dad-49d5-aa0b-79cc072fe0ef] Video saved to temporary file: temp_videos/dc27d7c0-3dad-49d5-aa0b-79cc072fe0ef.mp4 | |
| 2025-08-20 23:47:42 - INFO - [dc27d7c0-3dad-49d5-aa0b-79cc072fe0ef] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:47:47 - INFO - [dc27d7c0-3dad-49d5-aa0b-79cc072fe0ef] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:47:47 - INFO - [dc27d7c0-3dad-49d5-aa0b-79cc072fe0ef] 30 frames saved to temp_videos/dc27d7c0-3dad-49d5-aa0b-79cc072fe0ef | |
| 2025-08-20 23:48:00 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:48:15 - INFO - Tokens per second: 7.993319182461253, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:48:15 - INFO - [dc27d7c0-3dad-49d5-aa0b-79cc072fe0ef] Inference time: 33.46 seconds, CPU usage: 35.9%, CPU core utilization: [55.1, 38.2, 24.9, 25.4] | |
| 2025-08-20 23:48:15 - INFO - [dc27d7c0-3dad-49d5-aa0b-79cc072fe0ef] Cleaned up temporary frame directory: temp_videos/dc27d7c0-3dad-49d5-aa0b-79cc072fe0ef | |
| 2025-08-20 23:48:15 - INFO - [2d2b338a-5383-48df-a50c-a5469d4bf2a2] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_021.mp4' | |
| 2025-08-20 23:48:15 - INFO - [2d2b338a-5383-48df-a50c-a5469d4bf2a2] Video saved to temporary file: temp_videos/2d2b338a-5383-48df-a50c-a5469d4bf2a2.mp4 | |
| 2025-08-20 23:48:15 - INFO - [2d2b338a-5383-48df-a50c-a5469d4bf2a2] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:48:20 - INFO - [2d2b338a-5383-48df-a50c-a5469d4bf2a2] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:48:20 - INFO - [2d2b338a-5383-48df-a50c-a5469d4bf2a2] 30 frames saved to temp_videos/2d2b338a-5383-48df-a50c-a5469d4bf2a2 | |
| 2025-08-20 23:48:33 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:48:50 - INFO - Tokens per second: 8.475114910409703, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:48:50 - INFO - [2d2b338a-5383-48df-a50c-a5469d4bf2a2] Inference time: 34.69 seconds, CPU usage: 35.2%, CPU core utilization: [23.3, 27.9, 41.5, 48.1] | |
| 2025-08-20 23:48:50 - INFO - [2d2b338a-5383-48df-a50c-a5469d4bf2a2] Cleaned up temporary frame directory: temp_videos/2d2b338a-5383-48df-a50c-a5469d4bf2a2 | |
| 2025-08-20 23:48:50 - INFO - [91c7b79b-21ef-4745-a10e-22a03a1abd0c] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_022.mp4' | |
| 2025-08-20 23:48:50 - INFO - [91c7b79b-21ef-4745-a10e-22a03a1abd0c] Video saved to temporary file: temp_videos/91c7b79b-21ef-4745-a10e-22a03a1abd0c.mp4 | |
| 2025-08-20 23:48:50 - INFO - [91c7b79b-21ef-4745-a10e-22a03a1abd0c] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:48:55 - INFO - [91c7b79b-21ef-4745-a10e-22a03a1abd0c] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:48:55 - INFO - [91c7b79b-21ef-4745-a10e-22a03a1abd0c] 30 frames saved to temp_videos/91c7b79b-21ef-4745-a10e-22a03a1abd0c | |
| 2025-08-20 23:49:08 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:49:23 - INFO - Tokens per second: 7.968927639160867, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:49:23 - INFO - [91c7b79b-21ef-4745-a10e-22a03a1abd0c] Inference time: 33.28 seconds, CPU usage: 35.7%, CPU core utilization: [63.9, 25.4, 38.6, 14.6] | |
| 2025-08-20 23:49:23 - INFO - [91c7b79b-21ef-4745-a10e-22a03a1abd0c] Cleaned up temporary frame directory: temp_videos/91c7b79b-21ef-4745-a10e-22a03a1abd0c | |
| 2025-08-20 23:49:23 - INFO - [5139cda6-0da8-43e9-8f70-5adf1590238b] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_023.mp4' | |
| 2025-08-20 23:49:23 - INFO - [5139cda6-0da8-43e9-8f70-5adf1590238b] Video saved to temporary file: temp_videos/5139cda6-0da8-43e9-8f70-5adf1590238b.mp4 | |
| 2025-08-20 23:49:23 - INFO - [5139cda6-0da8-43e9-8f70-5adf1590238b] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:49:28 - INFO - [5139cda6-0da8-43e9-8f70-5adf1590238b] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:49:28 - INFO - [5139cda6-0da8-43e9-8f70-5adf1590238b] 30 frames saved to temp_videos/5139cda6-0da8-43e9-8f70-5adf1590238b | |
| 2025-08-20 23:49:41 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:49:55 - INFO - Tokens per second: 7.454720470818721, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:49:55 - INFO - [5139cda6-0da8-43e9-8f70-5adf1590238b] Inference time: 32.14 seconds, CPU usage: 35.9%, CPU core utilization: [54.3, 22.4, 50.0, 17.0] | |
| 2025-08-20 23:49:55 - INFO - [5139cda6-0da8-43e9-8f70-5adf1590238b] Cleaned up temporary frame directory: temp_videos/5139cda6-0da8-43e9-8f70-5adf1590238b | |
| 2025-08-20 23:49:55 - INFO - [b92496ee-5a36-490d-aadb-2f06439d7995] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_024.mp4' | |
| 2025-08-20 23:49:55 - INFO - [b92496ee-5a36-490d-aadb-2f06439d7995] Video saved to temporary file: temp_videos/b92496ee-5a36-490d-aadb-2f06439d7995.mp4 | |
| 2025-08-20 23:49:55 - INFO - [b92496ee-5a36-490d-aadb-2f06439d7995] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:50:00 - INFO - [b92496ee-5a36-490d-aadb-2f06439d7995] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:50:00 - INFO - [b92496ee-5a36-490d-aadb-2f06439d7995] 30 frames saved to temp_videos/b92496ee-5a36-490d-aadb-2f06439d7995 | |
| 2025-08-20 23:50:13 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:50:29 - INFO - Tokens per second: 8.25678903581856, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:50:29 - INFO - [b92496ee-5a36-490d-aadb-2f06439d7995] Inference time: 34.09 seconds, CPU usage: 35.5%, CPU core utilization: [51.5, 45.5, 16.6, 28.4] | |
| 2025-08-20 23:50:29 - INFO - [b92496ee-5a36-490d-aadb-2f06439d7995] Cleaned up temporary frame directory: temp_videos/b92496ee-5a36-490d-aadb-2f06439d7995 | |
| 2025-08-20 23:50:29 - INFO - [4ecf6faf-4096-491c-8670-2c39714858dc] Received new video inference request. Prompt: 'Summarize the key events in this convenience store video. Focus only on the actions and interactions of the people. Avoid repetitive descriptions of the store's layout or shelves.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_025.mp4' | |
| 2025-08-20 23:50:29 - INFO - [4ecf6faf-4096-491c-8670-2c39714858dc] Video saved to temporary file: temp_videos/4ecf6faf-4096-491c-8670-2c39714858dc.mp4 | |
| 2025-08-20 23:50:29 - INFO - [4ecf6faf-4096-491c-8670-2c39714858dc] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:50:34 - INFO - [4ecf6faf-4096-491c-8670-2c39714858dc] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:50:34 - INFO - [4ecf6faf-4096-491c-8670-2c39714858dc] 30 frames saved to temp_videos/4ecf6faf-4096-491c-8670-2c39714858dc | |
| 2025-08-20 23:50:47 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:51:17 - INFO - Tokens per second: 10.736432842240825, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:51:17 - INFO - [4ecf6faf-4096-491c-8670-2c39714858dc] Inference time: 47.95 seconds, CPU usage: 33.5%, CPU core utilization: [38.6, 16.2, 63.7, 15.3] | |
| 2025-08-20 23:51:17 - INFO - [4ecf6faf-4096-491c-8670-2c39714858dc] Cleaned up temporary frame directory: temp_videos/4ecf6faf-4096-491c-8670-2c39714858dc | |
| 2025-08-20 23:54:07 - INFO - [380eb612-eca5-49dd-b2d1-bbdeb5ecf54c] 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' | |
| 2025-08-20 23:54:07 - INFO - [380eb612-eca5-49dd-b2d1-bbdeb5ecf54c] Video saved to temporary file: temp_videos/380eb612-eca5-49dd-b2d1-bbdeb5ecf54c.mp4 | |
| 2025-08-20 23:54:07 - INFO - [380eb612-eca5-49dd-b2d1-bbdeb5ecf54c] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:54:12 - INFO - [380eb612-eca5-49dd-b2d1-bbdeb5ecf54c] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:54:12 - INFO - [380eb612-eca5-49dd-b2d1-bbdeb5ecf54c] 30 frames saved to temp_videos/380eb612-eca5-49dd-b2d1-bbdeb5ecf54c | |
| 2025-08-20 23:54:25 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:54:37 - INFO - Tokens per second: 6.4951065299349615, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:54:37 - INFO - [380eb612-eca5-49dd-b2d1-bbdeb5ecf54c] Inference time: 29.85 seconds, CPU usage: 6.8%, CPU core utilization: [6.3, 7.3, 10.0, 3.6] | |
| 2025-08-20 23:54:37 - INFO - [380eb612-eca5-49dd-b2d1-bbdeb5ecf54c] Cleaned up temporary frame directory: temp_videos/380eb612-eca5-49dd-b2d1-bbdeb5ecf54c | |
| 2025-08-20 23:54:37 - INFO - [aee27771-15f4-4e39-89c7-953aaf2d6435] 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' | |
| 2025-08-20 23:54:37 - INFO - [aee27771-15f4-4e39-89c7-953aaf2d6435] Video saved to temporary file: temp_videos/aee27771-15f4-4e39-89c7-953aaf2d6435.mp4 | |
| 2025-08-20 23:54:37 - INFO - [aee27771-15f4-4e39-89c7-953aaf2d6435] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:54:42 - INFO - [aee27771-15f4-4e39-89c7-953aaf2d6435] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:54:42 - INFO - [aee27771-15f4-4e39-89c7-953aaf2d6435] 30 frames saved to temp_videos/aee27771-15f4-4e39-89c7-953aaf2d6435 | |
| 2025-08-20 23:54:55 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:55:04 - INFO - Tokens per second: 4.620365146287069, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:55:04 - INFO - [aee27771-15f4-4e39-89c7-953aaf2d6435] Inference time: 27.55 seconds, CPU usage: 37.7%, CPU core utilization: [23.5, 33.0, 45.6, 48.7] | |
| 2025-08-20 23:55:04 - INFO - [aee27771-15f4-4e39-89c7-953aaf2d6435] Cleaned up temporary frame directory: temp_videos/aee27771-15f4-4e39-89c7-953aaf2d6435 | |
| 2025-08-20 23:55:04 - INFO - [33034474-6cc6-44ea-bf4e-595b33e0a842] 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' | |
| 2025-08-20 23:55:04 - INFO - [33034474-6cc6-44ea-bf4e-595b33e0a842] Video saved to temporary file: temp_videos/33034474-6cc6-44ea-bf4e-595b33e0a842.mp4 | |
| 2025-08-20 23:55:04 - INFO - [33034474-6cc6-44ea-bf4e-595b33e0a842] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:55:09 - INFO - [33034474-6cc6-44ea-bf4e-595b33e0a842] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:55:09 - INFO - [33034474-6cc6-44ea-bf4e-595b33e0a842] 30 frames saved to temp_videos/33034474-6cc6-44ea-bf4e-595b33e0a842 | |
| 2025-08-20 23:55:22 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:55:35 - INFO - Tokens per second: 6.8004162288880075, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:55:35 - INFO - [33034474-6cc6-44ea-bf4e-595b33e0a842] Inference time: 30.57 seconds, CPU usage: 36.6%, CPU core utilization: [23.5, 34.8, 48.2, 39.9] | |
| 2025-08-20 23:55:35 - INFO - [33034474-6cc6-44ea-bf4e-595b33e0a842] Cleaned up temporary frame directory: temp_videos/33034474-6cc6-44ea-bf4e-595b33e0a842 | |
| 2025-08-20 23:55:35 - INFO - [08e94b4d-f36d-44c5-b12a-d657bad86595] 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' | |
| 2025-08-20 23:55:35 - INFO - [08e94b4d-f36d-44c5-b12a-d657bad86595] Video saved to temporary file: temp_videos/08e94b4d-f36d-44c5-b12a-d657bad86595.mp4 | |
| 2025-08-20 23:55:35 - INFO - [08e94b4d-f36d-44c5-b12a-d657bad86595] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:55:40 - INFO - [08e94b4d-f36d-44c5-b12a-d657bad86595] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:55:40 - INFO - [08e94b4d-f36d-44c5-b12a-d657bad86595] 30 frames saved to temp_videos/08e94b4d-f36d-44c5-b12a-d657bad86595 | |
| 2025-08-20 23:55:53 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:56:04 - INFO - Tokens per second: 5.72115634822065, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:56:04 - INFO - [08e94b4d-f36d-44c5-b12a-d657bad86595] Inference time: 29.03 seconds, CPU usage: 36.6%, CPU core utilization: [18.2, 59.9, 52.6, 16.0] | |
| 2025-08-20 23:56:04 - INFO - [08e94b4d-f36d-44c5-b12a-d657bad86595] Cleaned up temporary frame directory: temp_videos/08e94b4d-f36d-44c5-b12a-d657bad86595 | |
| 2025-08-20 23:56:04 - INFO - [aeba9bb8-25b3-44c0-8827-e08f9da881f5] 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' | |
| 2025-08-20 23:56:04 - INFO - [aeba9bb8-25b3-44c0-8827-e08f9da881f5] Video saved to temporary file: temp_videos/aeba9bb8-25b3-44c0-8827-e08f9da881f5.mp4 | |
| 2025-08-20 23:56:04 - INFO - [aeba9bb8-25b3-44c0-8827-e08f9da881f5] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:56:09 - INFO - [aeba9bb8-25b3-44c0-8827-e08f9da881f5] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:56:09 - INFO - [aeba9bb8-25b3-44c0-8827-e08f9da881f5] 30 frames saved to temp_videos/aeba9bb8-25b3-44c0-8827-e08f9da881f5 | |
| 2025-08-20 23:56:22 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:56:32 - INFO - Tokens per second: 4.8389257523545774, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:56:32 - INFO - [aeba9bb8-25b3-44c0-8827-e08f9da881f5] Inference time: 28.02 seconds, CPU usage: 37.2%, CPU core utilization: [18.8, 20.2, 51.9, 57.8] | |
| 2025-08-20 23:56:32 - INFO - [aeba9bb8-25b3-44c0-8827-e08f9da881f5] Cleaned up temporary frame directory: temp_videos/aeba9bb8-25b3-44c0-8827-e08f9da881f5 | |
| 2025-08-20 23:56:32 - INFO - [f59d2020-42d3-4106-ba4a-822cd7a913b9] 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' | |
| 2025-08-20 23:56:32 - INFO - [f59d2020-42d3-4106-ba4a-822cd7a913b9] Video saved to temporary file: temp_videos/f59d2020-42d3-4106-ba4a-822cd7a913b9.mp4 | |
| 2025-08-20 23:56:32 - INFO - [f59d2020-42d3-4106-ba4a-822cd7a913b9] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:56:37 - INFO - [f59d2020-42d3-4106-ba4a-822cd7a913b9] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:56:37 - INFO - [f59d2020-42d3-4106-ba4a-822cd7a913b9] 30 frames saved to temp_videos/f59d2020-42d3-4106-ba4a-822cd7a913b9 | |
| 2025-08-20 23:56:50 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:57:01 - INFO - Tokens per second: 5.491475730408376, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:57:01 - INFO - [f59d2020-42d3-4106-ba4a-822cd7a913b9] Inference time: 28.85 seconds, CPU usage: 36.8%, CPU core utilization: [19.5, 63.2, 31.2, 33.4] | |
| 2025-08-20 23:57:01 - INFO - [f59d2020-42d3-4106-ba4a-822cd7a913b9] Cleaned up temporary frame directory: temp_videos/f59d2020-42d3-4106-ba4a-822cd7a913b9 | |
| 2025-08-20 23:57:01 - INFO - [10f4ed0e-10c6-4a0e-baef-cbc5a15a174c] 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' | |
| 2025-08-20 23:57:01 - INFO - [10f4ed0e-10c6-4a0e-baef-cbc5a15a174c] Video saved to temporary file: temp_videos/10f4ed0e-10c6-4a0e-baef-cbc5a15a174c.mp4 | |
| 2025-08-20 23:57:01 - INFO - [10f4ed0e-10c6-4a0e-baef-cbc5a15a174c] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:57:06 - INFO - [10f4ed0e-10c6-4a0e-baef-cbc5a15a174c] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:57:06 - INFO - [10f4ed0e-10c6-4a0e-baef-cbc5a15a174c] 30 frames saved to temp_videos/10f4ed0e-10c6-4a0e-baef-cbc5a15a174c | |
| 2025-08-20 23:57:19 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:57:30 - INFO - Tokens per second: 5.435457465325606, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:57:30 - INFO - [10f4ed0e-10c6-4a0e-baef-cbc5a15a174c] Inference time: 28.75 seconds, CPU usage: 37.6%, CPU core utilization: [28.1, 30.6, 71.4, 20.3] | |
| 2025-08-20 23:57:30 - INFO - [10f4ed0e-10c6-4a0e-baef-cbc5a15a174c] Cleaned up temporary frame directory: temp_videos/10f4ed0e-10c6-4a0e-baef-cbc5a15a174c | |
| 2025-08-20 23:57:30 - INFO - [5a373da4-23c9-4001-93b0-2b33e1830f66] 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' | |
| 2025-08-20 23:57:30 - INFO - [5a373da4-23c9-4001-93b0-2b33e1830f66] Video saved to temporary file: temp_videos/5a373da4-23c9-4001-93b0-2b33e1830f66.mp4 | |
| 2025-08-20 23:57:30 - INFO - [5a373da4-23c9-4001-93b0-2b33e1830f66] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:57:35 - INFO - [5a373da4-23c9-4001-93b0-2b33e1830f66] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:57:35 - INFO - [5a373da4-23c9-4001-93b0-2b33e1830f66] 30 frames saved to temp_videos/5a373da4-23c9-4001-93b0-2b33e1830f66 | |
| 2025-08-20 23:57:48 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:57:58 - INFO - Tokens per second: 4.895421462414148, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:57:58 - INFO - [5a373da4-23c9-4001-93b0-2b33e1830f66] Inference time: 28.19 seconds, CPU usage: 37.4%, CPU core utilization: [27.1, 35.4, 25.4, 61.8] | |
| 2025-08-20 23:57:58 - INFO - [5a373da4-23c9-4001-93b0-2b33e1830f66] Cleaned up temporary frame directory: temp_videos/5a373da4-23c9-4001-93b0-2b33e1830f66 | |
| 2025-08-20 23:57:58 - INFO - [3b4f5fd8-cb88-4655-b977-6866088b99b9] 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' | |
| 2025-08-20 23:57:58 - INFO - [3b4f5fd8-cb88-4655-b977-6866088b99b9] Video saved to temporary file: temp_videos/3b4f5fd8-cb88-4655-b977-6866088b99b9.mp4 | |
| 2025-08-20 23:57:58 - INFO - [3b4f5fd8-cb88-4655-b977-6866088b99b9] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:58:03 - INFO - [3b4f5fd8-cb88-4655-b977-6866088b99b9] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:58:03 - INFO - [3b4f5fd8-cb88-4655-b977-6866088b99b9] 30 frames saved to temp_videos/3b4f5fd8-cb88-4655-b977-6866088b99b9 | |
| 2025-08-20 23:58:16 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:58:28 - INFO - Tokens per second: 6.246345549948331, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:58:28 - INFO - [3b4f5fd8-cb88-4655-b977-6866088b99b9] Inference time: 29.96 seconds, CPU usage: 36.8%, CPU core utilization: [36.0, 58.0, 37.8, 15.2] | |
| 2025-08-20 23:58:28 - INFO - [3b4f5fd8-cb88-4655-b977-6866088b99b9] Cleaned up temporary frame directory: temp_videos/3b4f5fd8-cb88-4655-b977-6866088b99b9 | |
| 2025-08-20 23:58:28 - INFO - [db892fe2-bfd0-4e5d-9afe-9740e936d083] 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' | |
| 2025-08-20 23:58:28 - INFO - [db892fe2-bfd0-4e5d-9afe-9740e936d083] Video saved to temporary file: temp_videos/db892fe2-bfd0-4e5d-9afe-9740e936d083.mp4 | |
| 2025-08-20 23:58:28 - INFO - [db892fe2-bfd0-4e5d-9afe-9740e936d083] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:58:33 - INFO - [db892fe2-bfd0-4e5d-9afe-9740e936d083] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:58:33 - INFO - [db892fe2-bfd0-4e5d-9afe-9740e936d083] 30 frames saved to temp_videos/db892fe2-bfd0-4e5d-9afe-9740e936d083 | |
| 2025-08-20 23:58:46 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:59:01 - INFO - Tokens per second: 7.823522467010842, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:59:01 - INFO - [db892fe2-bfd0-4e5d-9afe-9740e936d083] Inference time: 32.94 seconds, CPU usage: 35.7%, CPU core utilization: [52.5, 23.9, 22.6, 43.7] | |
| 2025-08-20 23:59:01 - INFO - [db892fe2-bfd0-4e5d-9afe-9740e936d083] Cleaned up temporary frame directory: temp_videos/db892fe2-bfd0-4e5d-9afe-9740e936d083 | |
| 2025-08-20 23:59:01 - INFO - [2c42d84f-5110-43d0-8b9a-70073da685d1] 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_011.mp4' | |
| 2025-08-20 23:59:01 - INFO - [2c42d84f-5110-43d0-8b9a-70073da685d1] Video saved to temporary file: temp_videos/2c42d84f-5110-43d0-8b9a-70073da685d1.mp4 | |
| 2025-08-20 23:59:01 - INFO - [2c42d84f-5110-43d0-8b9a-70073da685d1] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:59:06 - INFO - [2c42d84f-5110-43d0-8b9a-70073da685d1] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:59:06 - INFO - [2c42d84f-5110-43d0-8b9a-70073da685d1] 30 frames saved to temp_videos/2c42d84f-5110-43d0-8b9a-70073da685d1 | |
| 2025-08-20 23:59:19 - INFO - vision_config is None, using default vision config | |
| 2025-08-20 23:59:30 - INFO - Tokens per second: 5.483772695220153, Peak GPU memory MB: 11824.375 | |
| 2025-08-20 23:59:30 - INFO - [2c42d84f-5110-43d0-8b9a-70073da685d1] Inference time: 28.90 seconds, CPU usage: 37.2%, CPU core utilization: [18.5, 41.5, 21.7, 67.3] | |
| 2025-08-20 23:59:30 - INFO - [2c42d84f-5110-43d0-8b9a-70073da685d1] Cleaned up temporary frame directory: temp_videos/2c42d84f-5110-43d0-8b9a-70073da685d1 | |
| 2025-08-20 23:59:30 - INFO - [2872bdf2-bc5e-418d-8cae-07911540d748] 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_012.mp4' | |
| 2025-08-20 23:59:30 - INFO - [2872bdf2-bc5e-418d-8cae-07911540d748] Video saved to temporary file: temp_videos/2872bdf2-bc5e-418d-8cae-07911540d748.mp4 | |
| 2025-08-20 23:59:30 - INFO - [2872bdf2-bc5e-418d-8cae-07911540d748] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-20 23:59:35 - INFO - [2872bdf2-bc5e-418d-8cae-07911540d748] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-20 23:59:35 - INFO - [2872bdf2-bc5e-418d-8cae-07911540d748] 30 frames saved to temp_videos/2872bdf2-bc5e-418d-8cae-07911540d748 | |
| 2025-08-20 23:59:48 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:00:00 - INFO - Tokens per second: 6.375310581123721, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:00:00 - INFO - [2872bdf2-bc5e-418d-8cae-07911540d748] Inference time: 30.13 seconds, CPU usage: 37.0%, CPU core utilization: [32.4, 49.7, 41.4, 24.4] | |
| 2025-08-21 00:00:00 - INFO - [2872bdf2-bc5e-418d-8cae-07911540d748] Cleaned up temporary frame directory: temp_videos/2872bdf2-bc5e-418d-8cae-07911540d748 | |
| 2025-08-21 00:00:00 - INFO - [32bd674d-1546-4df6-9cb2-910789260e3b] 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_013.mp4' | |
| 2025-08-21 00:00:00 - INFO - [32bd674d-1546-4df6-9cb2-910789260e3b] Video saved to temporary file: temp_videos/32bd674d-1546-4df6-9cb2-910789260e3b.mp4 | |
| 2025-08-21 00:00:00 - INFO - [32bd674d-1546-4df6-9cb2-910789260e3b] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:00:05 - INFO - [32bd674d-1546-4df6-9cb2-910789260e3b] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:00:05 - INFO - [32bd674d-1546-4df6-9cb2-910789260e3b] 30 frames saved to temp_videos/32bd674d-1546-4df6-9cb2-910789260e3b | |
| 2025-08-21 00:00:18 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:00:30 - INFO - Tokens per second: 6.371663181689808, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:00:30 - INFO - [32bd674d-1546-4df6-9cb2-910789260e3b] Inference time: 30.19 seconds, CPU usage: 38.7%, CPU core utilization: [25.3, 24.5, 51.5, 53.1] | |
| 2025-08-21 00:00:30 - INFO - [32bd674d-1546-4df6-9cb2-910789260e3b] Cleaned up temporary frame directory: temp_videos/32bd674d-1546-4df6-9cb2-910789260e3b | |
| 2025-08-21 00:00:30 - INFO - [b8254b3e-b84d-4015-b0f1-46653b45a403] 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_014.mp4' | |
| 2025-08-21 00:00:30 - INFO - [b8254b3e-b84d-4015-b0f1-46653b45a403] Video saved to temporary file: temp_videos/b8254b3e-b84d-4015-b0f1-46653b45a403.mp4 | |
| 2025-08-21 00:00:30 - INFO - [b8254b3e-b84d-4015-b0f1-46653b45a403] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:00:35 - INFO - [b8254b3e-b84d-4015-b0f1-46653b45a403] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:00:35 - INFO - [b8254b3e-b84d-4015-b0f1-46653b45a403] 30 frames saved to temp_videos/b8254b3e-b84d-4015-b0f1-46653b45a403 | |
| 2025-08-21 00:00:48 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:01:00 - INFO - Tokens per second: 6.242465092882211, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:01:00 - INFO - [b8254b3e-b84d-4015-b0f1-46653b45a403] Inference time: 29.93 seconds, CPU usage: 36.6%, CPU core utilization: [43.4, 16.4, 27.8, 58.6] | |
| 2025-08-21 00:01:00 - INFO - [b8254b3e-b84d-4015-b0f1-46653b45a403] Cleaned up temporary frame directory: temp_videos/b8254b3e-b84d-4015-b0f1-46653b45a403 | |
| 2025-08-21 00:01:00 - INFO - [b9ea4590-07b7-4d5d-934d-ee43d847cbe4] 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_015.mp4' | |
| 2025-08-21 00:01:00 - INFO - [b9ea4590-07b7-4d5d-934d-ee43d847cbe4] Video saved to temporary file: temp_videos/b9ea4590-07b7-4d5d-934d-ee43d847cbe4.mp4 | |
| 2025-08-21 00:01:00 - INFO - [b9ea4590-07b7-4d5d-934d-ee43d847cbe4] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:01:05 - INFO - [b9ea4590-07b7-4d5d-934d-ee43d847cbe4] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:01:05 - INFO - [b9ea4590-07b7-4d5d-934d-ee43d847cbe4] 30 frames saved to temp_videos/b9ea4590-07b7-4d5d-934d-ee43d847cbe4 | |
| 2025-08-21 00:01:18 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:01:31 - INFO - Tokens per second: 6.8003448292571615, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:01:31 - INFO - [b9ea4590-07b7-4d5d-934d-ee43d847cbe4] Inference time: 30.82 seconds, CPU usage: 36.4%, CPU core utilization: [76.2, 16.3, 36.4, 16.7] | |
| 2025-08-21 00:01:31 - INFO - [b9ea4590-07b7-4d5d-934d-ee43d847cbe4] Cleaned up temporary frame directory: temp_videos/b9ea4590-07b7-4d5d-934d-ee43d847cbe4 | |
| 2025-08-21 00:01:31 - INFO - [8570af4d-c6dc-4f35-9db8-610d6f2e46d8] 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_016.mp4' | |
| 2025-08-21 00:01:31 - INFO - [8570af4d-c6dc-4f35-9db8-610d6f2e46d8] Video saved to temporary file: temp_videos/8570af4d-c6dc-4f35-9db8-610d6f2e46d8.mp4 | |
| 2025-08-21 00:01:31 - INFO - [8570af4d-c6dc-4f35-9db8-610d6f2e46d8] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:01:36 - INFO - [8570af4d-c6dc-4f35-9db8-610d6f2e46d8] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:01:36 - INFO - [8570af4d-c6dc-4f35-9db8-610d6f2e46d8] 30 frames saved to temp_videos/8570af4d-c6dc-4f35-9db8-610d6f2e46d8 | |
| 2025-08-21 00:01:49 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:02:01 - INFO - Tokens per second: 6.328218691218011, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:02:01 - INFO - [8570af4d-c6dc-4f35-9db8-610d6f2e46d8] Inference time: 30.10 seconds, CPU usage: 36.5%, CPU core utilization: [24.4, 22.4, 15.9, 83.2] | |
| 2025-08-21 00:02:01 - INFO - [8570af4d-c6dc-4f35-9db8-610d6f2e46d8] Cleaned up temporary frame directory: temp_videos/8570af4d-c6dc-4f35-9db8-610d6f2e46d8 | |
| 2025-08-21 00:02:01 - INFO - [576c0d47-06ea-44af-8aa5-2463af7c8cf7] 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_017.mp4' | |
| 2025-08-21 00:02:01 - INFO - [576c0d47-06ea-44af-8aa5-2463af7c8cf7] Video saved to temporary file: temp_videos/576c0d47-06ea-44af-8aa5-2463af7c8cf7.mp4 | |
| 2025-08-21 00:02:01 - INFO - [576c0d47-06ea-44af-8aa5-2463af7c8cf7] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:02:06 - INFO - [576c0d47-06ea-44af-8aa5-2463af7c8cf7] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:02:06 - INFO - [576c0d47-06ea-44af-8aa5-2463af7c8cf7] 30 frames saved to temp_videos/576c0d47-06ea-44af-8aa5-2463af7c8cf7 | |
| 2025-08-21 00:02:19 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:02:30 - INFO - Tokens per second: 5.366089856961263, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:02:30 - INFO - [576c0d47-06ea-44af-8aa5-2463af7c8cf7] Inference time: 28.73 seconds, CPU usage: 37.3%, CPU core utilization: [35.5, 35.8, 41.0, 36.9] | |
| 2025-08-21 00:02:30 - INFO - [576c0d47-06ea-44af-8aa5-2463af7c8cf7] Cleaned up temporary frame directory: temp_videos/576c0d47-06ea-44af-8aa5-2463af7c8cf7 | |
| 2025-08-21 00:02:30 - INFO - [247d4e66-1ef1-4d9e-9fa5-4fa5c66aa016] 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_018.mp4' | |
| 2025-08-21 00:02:30 - INFO - [247d4e66-1ef1-4d9e-9fa5-4fa5c66aa016] Video saved to temporary file: temp_videos/247d4e66-1ef1-4d9e-9fa5-4fa5c66aa016.mp4 | |
| 2025-08-21 00:02:30 - INFO - [247d4e66-1ef1-4d9e-9fa5-4fa5c66aa016] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:02:35 - INFO - [247d4e66-1ef1-4d9e-9fa5-4fa5c66aa016] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:02:35 - INFO - [247d4e66-1ef1-4d9e-9fa5-4fa5c66aa016] 30 frames saved to temp_videos/247d4e66-1ef1-4d9e-9fa5-4fa5c66aa016 | |
| 2025-08-21 00:02:48 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:03:01 - INFO - Tokens per second: 7.211379440337794, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:03:01 - INFO - [247d4e66-1ef1-4d9e-9fa5-4fa5c66aa016] Inference time: 31.65 seconds, CPU usage: 36.4%, CPU core utilization: [47.5, 23.3, 51.7, 23.0] | |
| 2025-08-21 00:03:01 - INFO - [247d4e66-1ef1-4d9e-9fa5-4fa5c66aa016] Cleaned up temporary frame directory: temp_videos/247d4e66-1ef1-4d9e-9fa5-4fa5c66aa016 | |
| 2025-08-21 00:03:02 - INFO - [84e77116-c87b-4b39-8001-7954bd84f3fd] 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_019.mp4' | |
| 2025-08-21 00:03:02 - INFO - [84e77116-c87b-4b39-8001-7954bd84f3fd] Video saved to temporary file: temp_videos/84e77116-c87b-4b39-8001-7954bd84f3fd.mp4 | |
| 2025-08-21 00:03:02 - INFO - [84e77116-c87b-4b39-8001-7954bd84f3fd] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:03:06 - INFO - [84e77116-c87b-4b39-8001-7954bd84f3fd] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:03:06 - INFO - [84e77116-c87b-4b39-8001-7954bd84f3fd] 30 frames saved to temp_videos/84e77116-c87b-4b39-8001-7954bd84f3fd | |
| 2025-08-21 00:03:19 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:03:30 - INFO - Tokens per second: 5.540220507070647, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:03:30 - INFO - [84e77116-c87b-4b39-8001-7954bd84f3fd] Inference time: 28.94 seconds, CPU usage: 37.0%, CPU core utilization: [33.0, 54.7, 43.2, 17.3] | |
| 2025-08-21 00:03:30 - INFO - [84e77116-c87b-4b39-8001-7954bd84f3fd] Cleaned up temporary frame directory: temp_videos/84e77116-c87b-4b39-8001-7954bd84f3fd | |
| 2025-08-21 00:03:30 - INFO - [988d9b75-c51b-4171-9ced-1e7ec41af950] 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_020.mp4' | |
| 2025-08-21 00:03:30 - INFO - [988d9b75-c51b-4171-9ced-1e7ec41af950] Video saved to temporary file: temp_videos/988d9b75-c51b-4171-9ced-1e7ec41af950.mp4 | |
| 2025-08-21 00:03:30 - INFO - [988d9b75-c51b-4171-9ced-1e7ec41af950] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:03:35 - INFO - [988d9b75-c51b-4171-9ced-1e7ec41af950] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:03:35 - INFO - [988d9b75-c51b-4171-9ced-1e7ec41af950] 30 frames saved to temp_videos/988d9b75-c51b-4171-9ced-1e7ec41af950 | |
| 2025-08-21 00:03:48 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:04:00 - INFO - Tokens per second: 6.098932177607684, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:04:00 - INFO - [988d9b75-c51b-4171-9ced-1e7ec41af950] Inference time: 29.66 seconds, CPU usage: 36.9%, CPU core utilization: [19.0, 31.2, 54.7, 42.7] | |
| 2025-08-21 00:04:00 - INFO - [988d9b75-c51b-4171-9ced-1e7ec41af950] Cleaned up temporary frame directory: temp_videos/988d9b75-c51b-4171-9ced-1e7ec41af950 | |
| 2025-08-21 00:04:00 - INFO - [ad9e17b9-f6e0-44d4-a882-cc7bde714ced] 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_021.mp4' | |
| 2025-08-21 00:04:00 - INFO - [ad9e17b9-f6e0-44d4-a882-cc7bde714ced] Video saved to temporary file: temp_videos/ad9e17b9-f6e0-44d4-a882-cc7bde714ced.mp4 | |
| 2025-08-21 00:04:00 - INFO - [ad9e17b9-f6e0-44d4-a882-cc7bde714ced] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:04:05 - INFO - [ad9e17b9-f6e0-44d4-a882-cc7bde714ced] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:04:05 - INFO - [ad9e17b9-f6e0-44d4-a882-cc7bde714ced] 30 frames saved to temp_videos/ad9e17b9-f6e0-44d4-a882-cc7bde714ced | |
| 2025-08-21 00:04:18 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:04:29 - INFO - Tokens per second: 5.256702476105206, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:04:29 - INFO - [ad9e17b9-f6e0-44d4-a882-cc7bde714ced] Inference time: 28.58 seconds, CPU usage: 37.3%, CPU core utilization: [41.7, 37.5, 52.9, 17.2] | |
| 2025-08-21 00:04:29 - INFO - [ad9e17b9-f6e0-44d4-a882-cc7bde714ced] Cleaned up temporary frame directory: temp_videos/ad9e17b9-f6e0-44d4-a882-cc7bde714ced | |
| 2025-08-21 00:04:29 - INFO - [55b659d8-42d1-481b-b2f4-d9ac78a772cd] 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_022.mp4' | |
| 2025-08-21 00:04:29 - INFO - [55b659d8-42d1-481b-b2f4-d9ac78a772cd] Video saved to temporary file: temp_videos/55b659d8-42d1-481b-b2f4-d9ac78a772cd.mp4 | |
| 2025-08-21 00:04:29 - INFO - [55b659d8-42d1-481b-b2f4-d9ac78a772cd] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:04:33 - INFO - [55b659d8-42d1-481b-b2f4-d9ac78a772cd] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:04:33 - INFO - [55b659d8-42d1-481b-b2f4-d9ac78a772cd] 30 frames saved to temp_videos/55b659d8-42d1-481b-b2f4-d9ac78a772cd | |
| 2025-08-21 00:04:46 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:04:55 - INFO - Tokens per second: 2.3146754530784004, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:04:55 - INFO - [55b659d8-42d1-481b-b2f4-d9ac78a772cd] Inference time: 25.85 seconds, CPU usage: 38.1%, CPU core utilization: [69.0, 33.5, 30.6, 19.4] | |
| 2025-08-21 00:04:55 - INFO - [55b659d8-42d1-481b-b2f4-d9ac78a772cd] Cleaned up temporary frame directory: temp_videos/55b659d8-42d1-481b-b2f4-d9ac78a772cd | |
| 2025-08-21 00:04:55 - INFO - [e8440f1e-8228-4173-8d4e-75e3bd0655f0] 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_023.mp4' | |
| 2025-08-21 00:04:55 - INFO - [e8440f1e-8228-4173-8d4e-75e3bd0655f0] Video saved to temporary file: temp_videos/e8440f1e-8228-4173-8d4e-75e3bd0655f0.mp4 | |
| 2025-08-21 00:04:55 - INFO - [e8440f1e-8228-4173-8d4e-75e3bd0655f0] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:04:59 - INFO - [e8440f1e-8228-4173-8d4e-75e3bd0655f0] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:04:59 - INFO - [e8440f1e-8228-4173-8d4e-75e3bd0655f0] 30 frames saved to temp_videos/e8440f1e-8228-4173-8d4e-75e3bd0655f0 | |
| 2025-08-21 00:05:12 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:05:23 - INFO - Tokens per second: 4.957384579566463, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:05:23 - INFO - [e8440f1e-8228-4173-8d4e-75e3bd0655f0] Inference time: 28.24 seconds, CPU usage: 37.5%, CPU core utilization: [33.0, 50.8, 47.3, 18.9] | |
| 2025-08-21 00:05:23 - INFO - [e8440f1e-8228-4173-8d4e-75e3bd0655f0] Cleaned up temporary frame directory: temp_videos/e8440f1e-8228-4173-8d4e-75e3bd0655f0 | |
| 2025-08-21 00:05:23 - INFO - [1f996954-f0cf-4ed2-813a-0fe738be6d01] 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_024.mp4' | |
| 2025-08-21 00:05:23 - INFO - [1f996954-f0cf-4ed2-813a-0fe738be6d01] Video saved to temporary file: temp_videos/1f996954-f0cf-4ed2-813a-0fe738be6d01.mp4 | |
| 2025-08-21 00:05:23 - INFO - [1f996954-f0cf-4ed2-813a-0fe738be6d01] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:05:28 - INFO - [1f996954-f0cf-4ed2-813a-0fe738be6d01] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:05:28 - INFO - [1f996954-f0cf-4ed2-813a-0fe738be6d01] 30 frames saved to temp_videos/1f996954-f0cf-4ed2-813a-0fe738be6d01 | |
| 2025-08-21 00:05:41 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:05:55 - INFO - Tokens per second: 7.516056826941947, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:05:55 - INFO - [1f996954-f0cf-4ed2-813a-0fe738be6d01] Inference time: 32.20 seconds, CPU usage: 35.6%, CPU core utilization: [33.4, 36.1, 32.6, 40.1] | |
| 2025-08-21 00:05:55 - INFO - [1f996954-f0cf-4ed2-813a-0fe738be6d01] Cleaned up temporary frame directory: temp_videos/1f996954-f0cf-4ed2-813a-0fe738be6d01 | |
| 2025-08-21 00:05:55 - INFO - [0750de05-37d6-46f0-bd2c-9e1e5a7140f8] 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_025.mp4' | |
| 2025-08-21 00:05:55 - INFO - [0750de05-37d6-46f0-bd2c-9e1e5a7140f8] Video saved to temporary file: temp_videos/0750de05-37d6-46f0-bd2c-9e1e5a7140f8.mp4 | |
| 2025-08-21 00:05:55 - INFO - [0750de05-37d6-46f0-bd2c-9e1e5a7140f8] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:06:00 - INFO - [0750de05-37d6-46f0-bd2c-9e1e5a7140f8] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:06:00 - INFO - [0750de05-37d6-46f0-bd2c-9e1e5a7140f8] 30 frames saved to temp_videos/0750de05-37d6-46f0-bd2c-9e1e5a7140f8 | |
| 2025-08-21 00:06:13 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:06:23 - INFO - Tokens per second: 4.695294352922656, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:06:23 - INFO - [0750de05-37d6-46f0-bd2c-9e1e5a7140f8] Inference time: 27.94 seconds, CPU usage: 37.5%, CPU core utilization: [52.4, 21.4, 57.3, 18.7] | |
| 2025-08-21 00:06:23 - INFO - [0750de05-37d6-46f0-bd2c-9e1e5a7140f8] Cleaned up temporary frame directory: temp_videos/0750de05-37d6-46f0-bd2c-9e1e5a7140f8 | |
| 2025-08-21 00:06:23 - INFO - [01029caa-6289-4c40-9cbc-a4ae5a937946] 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_026.mp4' | |
| 2025-08-21 00:06:23 - INFO - [01029caa-6289-4c40-9cbc-a4ae5a937946] Video saved to temporary file: temp_videos/01029caa-6289-4c40-9cbc-a4ae5a937946.mp4 | |
| 2025-08-21 00:06:23 - INFO - [01029caa-6289-4c40-9cbc-a4ae5a937946] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:06:28 - INFO - [01029caa-6289-4c40-9cbc-a4ae5a937946] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:06:28 - INFO - [01029caa-6289-4c40-9cbc-a4ae5a937946] 30 frames saved to temp_videos/01029caa-6289-4c40-9cbc-a4ae5a937946 | |
| 2025-08-21 00:06:41 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:06:54 - INFO - Tokens per second: 6.726536746978091, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:06:54 - INFO - [01029caa-6289-4c40-9cbc-a4ae5a937946] Inference time: 30.64 seconds, CPU usage: 36.4%, CPU core utilization: [24.0, 59.4, 17.0, 45.3] | |
| 2025-08-21 00:06:54 - INFO - [01029caa-6289-4c40-9cbc-a4ae5a937946] Cleaned up temporary frame directory: temp_videos/01029caa-6289-4c40-9cbc-a4ae5a937946 | |
| 2025-08-21 00:06:54 - INFO - [f210db90-ebcd-4bb7-bbf4-c28a7a20457b] 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_027.mp4' | |
| 2025-08-21 00:06:54 - INFO - [f210db90-ebcd-4bb7-bbf4-c28a7a20457b] Video saved to temporary file: temp_videos/f210db90-ebcd-4bb7-bbf4-c28a7a20457b.mp4 | |
| 2025-08-21 00:06:54 - INFO - [f210db90-ebcd-4bb7-bbf4-c28a7a20457b] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:06:58 - INFO - [f210db90-ebcd-4bb7-bbf4-c28a7a20457b] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:06:58 - INFO - [f210db90-ebcd-4bb7-bbf4-c28a7a20457b] 30 frames saved to temp_videos/f210db90-ebcd-4bb7-bbf4-c28a7a20457b | |
| 2025-08-21 00:07:11 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:07:24 - INFO - Tokens per second: 6.553781610815721, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:07:24 - INFO - [f210db90-ebcd-4bb7-bbf4-c28a7a20457b] Inference time: 30.34 seconds, CPU usage: 36.5%, CPU core utilization: [32.0, 56.7, 38.4, 18.8] | |
| 2025-08-21 00:07:24 - INFO - [f210db90-ebcd-4bb7-bbf4-c28a7a20457b] Cleaned up temporary frame directory: temp_videos/f210db90-ebcd-4bb7-bbf4-c28a7a20457b | |
| 2025-08-21 00:07:24 - INFO - [c32e0c9f-bf3d-4cb5-a0da-af1e3e029c5c] 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_028.mp4' | |
| 2025-08-21 00:07:24 - INFO - [c32e0c9f-bf3d-4cb5-a0da-af1e3e029c5c] Video saved to temporary file: temp_videos/c32e0c9f-bf3d-4cb5-a0da-af1e3e029c5c.mp4 | |
| 2025-08-21 00:07:24 - INFO - [c32e0c9f-bf3d-4cb5-a0da-af1e3e029c5c] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:07:29 - INFO - [c32e0c9f-bf3d-4cb5-a0da-af1e3e029c5c] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:07:29 - INFO - [c32e0c9f-bf3d-4cb5-a0da-af1e3e029c5c] 30 frames saved to temp_videos/c32e0c9f-bf3d-4cb5-a0da-af1e3e029c5c | |
| 2025-08-21 00:07:42 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:07:55 - INFO - Tokens per second: 6.759111802459959, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:07:55 - INFO - [c32e0c9f-bf3d-4cb5-a0da-af1e3e029c5c] Inference time: 30.70 seconds, CPU usage: 36.3%, CPU core utilization: [31.2, 20.1, 76.9, 17.1] | |
| 2025-08-21 00:07:55 - INFO - [c32e0c9f-bf3d-4cb5-a0da-af1e3e029c5c] Cleaned up temporary frame directory: temp_videos/c32e0c9f-bf3d-4cb5-a0da-af1e3e029c5c | |
| 2025-08-21 00:07:55 - INFO - [9ca4ad09-6652-4495-9660-8e536730d426] 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_029.mp4' | |
| 2025-08-21 00:07:55 - INFO - [9ca4ad09-6652-4495-9660-8e536730d426] Video saved to temporary file: temp_videos/9ca4ad09-6652-4495-9660-8e536730d426.mp4 | |
| 2025-08-21 00:07:55 - INFO - [9ca4ad09-6652-4495-9660-8e536730d426] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:08:00 - INFO - [9ca4ad09-6652-4495-9660-8e536730d426] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:08:00 - INFO - [9ca4ad09-6652-4495-9660-8e536730d426] 30 frames saved to temp_videos/9ca4ad09-6652-4495-9660-8e536730d426 | |
| 2025-08-21 00:08:13 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:08:32 - INFO - Tokens per second: 9.263214649215994, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:08:32 - INFO - [9ca4ad09-6652-4495-9660-8e536730d426] Inference time: 37.69 seconds, CPU usage: 34.5%, CPU core utilization: [53.9, 19.4, 24.3, 40.4] | |
| 2025-08-21 00:08:32 - INFO - [9ca4ad09-6652-4495-9660-8e536730d426] Cleaned up temporary frame directory: temp_videos/9ca4ad09-6652-4495-9660-8e536730d426 | |
| 2025-08-21 00:08:32 - INFO - [df092fec-bdf9-43d3-bdc0-e3addd960939] 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_030.mp4' | |
| 2025-08-21 00:08:32 - INFO - [df092fec-bdf9-43d3-bdc0-e3addd960939] Video saved to temporary file: temp_videos/df092fec-bdf9-43d3-bdc0-e3addd960939.mp4 | |
| 2025-08-21 00:08:32 - INFO - [df092fec-bdf9-43d3-bdc0-e3addd960939] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:08:37 - INFO - [df092fec-bdf9-43d3-bdc0-e3addd960939] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:08:37 - INFO - [df092fec-bdf9-43d3-bdc0-e3addd960939] 30 frames saved to temp_videos/df092fec-bdf9-43d3-bdc0-e3addd960939 | |
| 2025-08-21 00:08:50 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:09:00 - INFO - Tokens per second: 4.063290188399236, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:09:00 - INFO - [df092fec-bdf9-43d3-bdc0-e3addd960939] Inference time: 27.34 seconds, CPU usage: 37.5%, CPU core utilization: [50.1, 20.2, 61.0, 18.7] | |
| 2025-08-21 00:09:00 - INFO - [df092fec-bdf9-43d3-bdc0-e3addd960939] Cleaned up temporary frame directory: temp_videos/df092fec-bdf9-43d3-bdc0-e3addd960939 | |
| 2025-08-21 00:09:00 - INFO - [ca418df5-894b-4902-ba9d-0e23d1dd86ab] 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_031.mp4' | |
| 2025-08-21 00:09:00 - INFO - [ca418df5-894b-4902-ba9d-0e23d1dd86ab] Video saved to temporary file: temp_videos/ca418df5-894b-4902-ba9d-0e23d1dd86ab.mp4 | |
| 2025-08-21 00:09:00 - INFO - [ca418df5-894b-4902-ba9d-0e23d1dd86ab] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:09:05 - INFO - [ca418df5-894b-4902-ba9d-0e23d1dd86ab] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:09:05 - INFO - [ca418df5-894b-4902-ba9d-0e23d1dd86ab] 30 frames saved to temp_videos/ca418df5-894b-4902-ba9d-0e23d1dd86ab | |
| 2025-08-21 00:09:17 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:09:31 - INFO - Tokens per second: 7.1731396320969125, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:09:31 - INFO - [ca418df5-894b-4902-ba9d-0e23d1dd86ab] Inference time: 31.49 seconds, CPU usage: 36.2%, CPU core utilization: [35.7, 20.6, 19.6, 68.6] | |
| 2025-08-21 00:09:31 - INFO - [ca418df5-894b-4902-ba9d-0e23d1dd86ab] Cleaned up temporary frame directory: temp_videos/ca418df5-894b-4902-ba9d-0e23d1dd86ab | |
| 2025-08-21 00:09:31 - INFO - [e88d0f9b-c698-414c-858d-003fae28cdf3] 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_032.mp4' | |
| 2025-08-21 00:09:31 - INFO - [e88d0f9b-c698-414c-858d-003fae28cdf3] Video saved to temporary file: temp_videos/e88d0f9b-c698-414c-858d-003fae28cdf3.mp4 | |
| 2025-08-21 00:09:31 - INFO - [e88d0f9b-c698-414c-858d-003fae28cdf3] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:09:36 - INFO - [e88d0f9b-c698-414c-858d-003fae28cdf3] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:09:36 - INFO - [e88d0f9b-c698-414c-858d-003fae28cdf3] 30 frames saved to temp_videos/e88d0f9b-c698-414c-858d-003fae28cdf3 | |
| 2025-08-21 00:09:49 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:10:02 - INFO - Tokens per second: 6.459775499170554, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:10:02 - INFO - [e88d0f9b-c698-414c-858d-003fae28cdf3] Inference time: 30.22 seconds, CPU usage: 36.5%, CPU core utilization: [40.0, 21.9, 46.6, 37.5] | |
| 2025-08-21 00:10:02 - INFO - [e88d0f9b-c698-414c-858d-003fae28cdf3] Cleaned up temporary frame directory: temp_videos/e88d0f9b-c698-414c-858d-003fae28cdf3 | |
| 2025-08-21 00:10:02 - INFO - [53a4ed5c-13d3-4b71-b5f6-ce4d784c05ae] 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_033.mp4' | |
| 2025-08-21 00:10:02 - INFO - [53a4ed5c-13d3-4b71-b5f6-ce4d784c05ae] Video saved to temporary file: temp_videos/53a4ed5c-13d3-4b71-b5f6-ce4d784c05ae.mp4 | |
| 2025-08-21 00:10:02 - INFO - [53a4ed5c-13d3-4b71-b5f6-ce4d784c05ae] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:10:06 - INFO - [53a4ed5c-13d3-4b71-b5f6-ce4d784c05ae] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:10:06 - INFO - [53a4ed5c-13d3-4b71-b5f6-ce4d784c05ae] 30 frames saved to temp_videos/53a4ed5c-13d3-4b71-b5f6-ce4d784c05ae | |
| 2025-08-21 00:10:19 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:10:37 - INFO - Tokens per second: 8.532561247112476, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:10:37 - INFO - [53a4ed5c-13d3-4b71-b5f6-ce4d784c05ae] Inference time: 34.97 seconds, CPU usage: 35.2%, CPU core utilization: [16.2, 20.7, 47.4, 56.6] | |
| 2025-08-21 00:10:37 - INFO - [53a4ed5c-13d3-4b71-b5f6-ce4d784c05ae] Cleaned up temporary frame directory: temp_videos/53a4ed5c-13d3-4b71-b5f6-ce4d784c05ae | |
| 2025-08-21 00:10:37 - INFO - [ccd7f7c1-6c22-4ee5-876a-1c19b01e0607] 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_034.mp4' | |
| 2025-08-21 00:10:37 - INFO - [ccd7f7c1-6c22-4ee5-876a-1c19b01e0607] Video saved to temporary file: temp_videos/ccd7f7c1-6c22-4ee5-876a-1c19b01e0607.mp4 | |
| 2025-08-21 00:10:37 - INFO - [ccd7f7c1-6c22-4ee5-876a-1c19b01e0607] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:10:41 - INFO - [ccd7f7c1-6c22-4ee5-876a-1c19b01e0607] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:10:41 - INFO - [ccd7f7c1-6c22-4ee5-876a-1c19b01e0607] 30 frames saved to temp_videos/ccd7f7c1-6c22-4ee5-876a-1c19b01e0607 | |
| 2025-08-21 00:10:54 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:11:06 - INFO - Tokens per second: 6.093386425880963, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:11:06 - INFO - [ccd7f7c1-6c22-4ee5-876a-1c19b01e0607] Inference time: 29.67 seconds, CPU usage: 36.6%, CPU core utilization: [47.7, 65.3, 17.1, 16.5] | |
| 2025-08-21 00:11:06 - INFO - [ccd7f7c1-6c22-4ee5-876a-1c19b01e0607] Cleaned up temporary frame directory: temp_videos/ccd7f7c1-6c22-4ee5-876a-1c19b01e0607 | |
| 2025-08-21 00:11:06 - INFO - [496ad230-f9e4-468b-9097-aae0d083dd17] 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_035.mp4' | |
| 2025-08-21 00:11:06 - INFO - [496ad230-f9e4-468b-9097-aae0d083dd17] Video saved to temporary file: temp_videos/496ad230-f9e4-468b-9097-aae0d083dd17.mp4 | |
| 2025-08-21 00:11:06 - INFO - [496ad230-f9e4-468b-9097-aae0d083dd17] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:11:11 - INFO - [496ad230-f9e4-468b-9097-aae0d083dd17] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:11:11 - INFO - [496ad230-f9e4-468b-9097-aae0d083dd17] 30 frames saved to temp_videos/496ad230-f9e4-468b-9097-aae0d083dd17 | |
| 2025-08-21 00:11:24 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:11:39 - INFO - Tokens per second: 7.846984662180754, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:11:39 - INFO - [496ad230-f9e4-468b-9097-aae0d083dd17] Inference time: 33.09 seconds, CPU usage: 35.7%, CPU core utilization: [14.8, 15.5, 59.9, 52.6] | |
| 2025-08-21 00:11:39 - INFO - [496ad230-f9e4-468b-9097-aae0d083dd17] Cleaned up temporary frame directory: temp_videos/496ad230-f9e4-468b-9097-aae0d083dd17 | |
| 2025-08-21 00:11:39 - INFO - [124ab1d5-65f5-4f6f-8641-57c4c85808d4] 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_036.mp4' | |
| 2025-08-21 00:11:39 - INFO - [124ab1d5-65f5-4f6f-8641-57c4c85808d4] Video saved to temporary file: temp_videos/124ab1d5-65f5-4f6f-8641-57c4c85808d4.mp4 | |
| 2025-08-21 00:11:39 - INFO - [124ab1d5-65f5-4f6f-8641-57c4c85808d4] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:11:44 - INFO - [124ab1d5-65f5-4f6f-8641-57c4c85808d4] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:11:44 - INFO - [124ab1d5-65f5-4f6f-8641-57c4c85808d4] 30 frames saved to temp_videos/124ab1d5-65f5-4f6f-8641-57c4c85808d4 | |
| 2025-08-21 00:11:57 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:12:07 - INFO - Tokens per second: 4.356472577241336, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:12:07 - INFO - [124ab1d5-65f5-4f6f-8641-57c4c85808d4] Inference time: 27.59 seconds, CPU usage: 37.4%, CPU core utilization: [20.9, 70.7, 18.3, 40.0] | |
| 2025-08-21 00:12:07 - INFO - [124ab1d5-65f5-4f6f-8641-57c4c85808d4] Cleaned up temporary frame directory: temp_videos/124ab1d5-65f5-4f6f-8641-57c4c85808d4 | |
| 2025-08-21 00:12:07 - INFO - [e52f096d-c451-4930-83cf-bb8210f55a92] 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_037.mp4' | |
| 2025-08-21 00:12:07 - INFO - [e52f096d-c451-4930-83cf-bb8210f55a92] Video saved to temporary file: temp_videos/e52f096d-c451-4930-83cf-bb8210f55a92.mp4 | |
| 2025-08-21 00:12:07 - INFO - [e52f096d-c451-4930-83cf-bb8210f55a92] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:12:12 - INFO - [e52f096d-c451-4930-83cf-bb8210f55a92] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:12:12 - INFO - [e52f096d-c451-4930-83cf-bb8210f55a92] 30 frames saved to temp_videos/e52f096d-c451-4930-83cf-bb8210f55a92 | |
| 2025-08-21 00:12:25 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:12:35 - INFO - Tokens per second: 5.138801059166309, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:12:35 - INFO - [e52f096d-c451-4930-83cf-bb8210f55a92] Inference time: 28.53 seconds, CPU usage: 37.3%, CPU core utilization: [47.6, 38.0, 17.4, 46.2] | |
| 2025-08-21 00:12:35 - INFO - [e52f096d-c451-4930-83cf-bb8210f55a92] Cleaned up temporary frame directory: temp_videos/e52f096d-c451-4930-83cf-bb8210f55a92 | |
| 2025-08-21 00:12:35 - INFO - [00c8bc41-e1e0-4ab7-8072-cd4bc78fe18a] 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_038.mp4' | |
| 2025-08-21 00:12:35 - INFO - [00c8bc41-e1e0-4ab7-8072-cd4bc78fe18a] Video saved to temporary file: temp_videos/00c8bc41-e1e0-4ab7-8072-cd4bc78fe18a.mp4 | |
| 2025-08-21 00:12:35 - INFO - [00c8bc41-e1e0-4ab7-8072-cd4bc78fe18a] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:12:40 - INFO - [00c8bc41-e1e0-4ab7-8072-cd4bc78fe18a] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:12:40 - INFO - [00c8bc41-e1e0-4ab7-8072-cd4bc78fe18a] 30 frames saved to temp_videos/00c8bc41-e1e0-4ab7-8072-cd4bc78fe18a | |
| 2025-08-21 00:12:53 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:13:02 - INFO - Tokens per second: 3.425754264592105, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:13:02 - INFO - [00c8bc41-e1e0-4ab7-8072-cd4bc78fe18a] Inference time: 26.76 seconds, CPU usage: 37.7%, CPU core utilization: [23.2, 51.9, 42.6, 33.3] | |
| 2025-08-21 00:13:02 - INFO - [00c8bc41-e1e0-4ab7-8072-cd4bc78fe18a] Cleaned up temporary frame directory: temp_videos/00c8bc41-e1e0-4ab7-8072-cd4bc78fe18a | |
| 2025-08-21 00:13:02 - INFO - [a840eac1-a5b6-435f-aceb-589aa77afa45] 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_039.mp4' | |
| 2025-08-21 00:13:02 - INFO - [a840eac1-a5b6-435f-aceb-589aa77afa45] Video saved to temporary file: temp_videos/a840eac1-a5b6-435f-aceb-589aa77afa45.mp4 | |
| 2025-08-21 00:13:02 - INFO - [a840eac1-a5b6-435f-aceb-589aa77afa45] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:13:07 - INFO - [a840eac1-a5b6-435f-aceb-589aa77afa45] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:13:07 - INFO - [a840eac1-a5b6-435f-aceb-589aa77afa45] 30 frames saved to temp_videos/a840eac1-a5b6-435f-aceb-589aa77afa45 | |
| 2025-08-21 00:13:20 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:13:30 - INFO - Tokens per second: 4.69602386319334, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:13:30 - INFO - [a840eac1-a5b6-435f-aceb-589aa77afa45] Inference time: 27.88 seconds, CPU usage: 37.3%, CPU core utilization: [51.3, 17.6, 19.3, 60.6] | |
| 2025-08-21 00:13:30 - INFO - [a840eac1-a5b6-435f-aceb-589aa77afa45] Cleaned up temporary frame directory: temp_videos/a840eac1-a5b6-435f-aceb-589aa77afa45 | |
| 2025-08-21 00:13:30 - INFO - [79fff7f5-155c-4aab-a7fd-d432cf110dde] 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_040.mp4' | |
| 2025-08-21 00:13:30 - INFO - [79fff7f5-155c-4aab-a7fd-d432cf110dde] Video saved to temporary file: temp_videos/79fff7f5-155c-4aab-a7fd-d432cf110dde.mp4 | |
| 2025-08-21 00:13:30 - INFO - [79fff7f5-155c-4aab-a7fd-d432cf110dde] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:13:35 - INFO - [79fff7f5-155c-4aab-a7fd-d432cf110dde] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:13:35 - INFO - [79fff7f5-155c-4aab-a7fd-d432cf110dde] 30 frames saved to temp_videos/79fff7f5-155c-4aab-a7fd-d432cf110dde | |
| 2025-08-21 00:13:48 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:14:06 - INFO - Tokens per second: 8.923322929883941, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:14:06 - INFO - [79fff7f5-155c-4aab-a7fd-d432cf110dde] Inference time: 36.23 seconds, CPU usage: 34.9%, CPU core utilization: [26.5, 17.6, 53.3, 42.2] | |
| 2025-08-21 00:14:06 - INFO - [79fff7f5-155c-4aab-a7fd-d432cf110dde] Cleaned up temporary frame directory: temp_videos/79fff7f5-155c-4aab-a7fd-d432cf110dde | |
| 2025-08-21 00:14:06 - INFO - [5a62181d-1328-4203-92fb-95497b40e1cf] 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_041.mp4' | |
| 2025-08-21 00:14:06 - INFO - [5a62181d-1328-4203-92fb-95497b40e1cf] Video saved to temporary file: temp_videos/5a62181d-1328-4203-92fb-95497b40e1cf.mp4 | |
| 2025-08-21 00:14:06 - INFO - [5a62181d-1328-4203-92fb-95497b40e1cf] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:14:11 - INFO - [5a62181d-1328-4203-92fb-95497b40e1cf] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:14:11 - INFO - [5a62181d-1328-4203-92fb-95497b40e1cf] 30 frames saved to temp_videos/5a62181d-1328-4203-92fb-95497b40e1cf | |
| 2025-08-21 00:14:24 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:14:37 - INFO - Tokens per second: 6.836469983622892, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:14:37 - INFO - [5a62181d-1328-4203-92fb-95497b40e1cf] Inference time: 31.03 seconds, CPU usage: 36.3%, CPU core utilization: [30.2, 49.8, 43.0, 22.1] | |
| 2025-08-21 00:14:37 - INFO - [5a62181d-1328-4203-92fb-95497b40e1cf] Cleaned up temporary frame directory: temp_videos/5a62181d-1328-4203-92fb-95497b40e1cf | |
| 2025-08-21 00:14:37 - INFO - [b8f2e591-45db-423c-9af0-ed74004baae0] 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_042.mp4' | |
| 2025-08-21 00:14:37 - INFO - [b8f2e591-45db-423c-9af0-ed74004baae0] Video saved to temporary file: temp_videos/b8f2e591-45db-423c-9af0-ed74004baae0.mp4 | |
| 2025-08-21 00:14:37 - INFO - [b8f2e591-45db-423c-9af0-ed74004baae0] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:14:42 - INFO - [b8f2e591-45db-423c-9af0-ed74004baae0] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:14:42 - INFO - [b8f2e591-45db-423c-9af0-ed74004baae0] 30 frames saved to temp_videos/b8f2e591-45db-423c-9af0-ed74004baae0 | |
| 2025-08-21 00:14:55 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:15:07 - INFO - Tokens per second: 5.799046418435553, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:15:07 - INFO - [b8f2e591-45db-423c-9af0-ed74004baae0] Inference time: 29.23 seconds, CPU usage: 36.6%, CPU core utilization: [52.7, 42.9, 16.9, 34.0] | |
| 2025-08-21 00:15:07 - INFO - [b8f2e591-45db-423c-9af0-ed74004baae0] Cleaned up temporary frame directory: temp_videos/b8f2e591-45db-423c-9af0-ed74004baae0 | |
| 2025-08-21 00:15:07 - INFO - [d32f2792-3f75-4bb2-803e-e3d8f5ab1a76] 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_043.mp4' | |
| 2025-08-21 00:15:07 - INFO - [d32f2792-3f75-4bb2-803e-e3d8f5ab1a76] Video saved to temporary file: temp_videos/d32f2792-3f75-4bb2-803e-e3d8f5ab1a76.mp4 | |
| 2025-08-21 00:15:07 - INFO - [d32f2792-3f75-4bb2-803e-e3d8f5ab1a76] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:15:12 - INFO - [d32f2792-3f75-4bb2-803e-e3d8f5ab1a76] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:15:12 - INFO - [d32f2792-3f75-4bb2-803e-e3d8f5ab1a76] 30 frames saved to temp_videos/d32f2792-3f75-4bb2-803e-e3d8f5ab1a76 | |
| 2025-08-21 00:15:25 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:15:40 - INFO - Tokens per second: 7.766284842271324, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:15:40 - INFO - [d32f2792-3f75-4bb2-803e-e3d8f5ab1a76] Inference time: 32.92 seconds, CPU usage: 35.7%, CPU core utilization: [16.6, 43.3, 58.1, 24.8] | |
| 2025-08-21 00:15:40 - INFO - [d32f2792-3f75-4bb2-803e-e3d8f5ab1a76] Cleaned up temporary frame directory: temp_videos/d32f2792-3f75-4bb2-803e-e3d8f5ab1a76 | |
| 2025-08-21 00:15:40 - INFO - [978e0423-475a-455d-aa66-ca499da86744] 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_044.mp4' | |
| 2025-08-21 00:15:40 - INFO - [978e0423-475a-455d-aa66-ca499da86744] Video saved to temporary file: temp_videos/978e0423-475a-455d-aa66-ca499da86744.mp4 | |
| 2025-08-21 00:15:40 - INFO - [978e0423-475a-455d-aa66-ca499da86744] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:15:44 - INFO - [978e0423-475a-455d-aa66-ca499da86744] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:15:44 - INFO - [978e0423-475a-455d-aa66-ca499da86744] 30 frames saved to temp_videos/978e0423-475a-455d-aa66-ca499da86744 | |
| 2025-08-21 00:15:57 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:16:07 - INFO - Tokens per second: 4.5631272946545245, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:16:07 - INFO - [978e0423-475a-455d-aa66-ca499da86744] Inference time: 27.84 seconds, CPU usage: 37.3%, CPU core utilization: [25.7, 32.6, 18.2, 72.5] | |
| 2025-08-21 00:16:07 - INFO - [978e0423-475a-455d-aa66-ca499da86744] Cleaned up temporary frame directory: temp_videos/978e0423-475a-455d-aa66-ca499da86744 | |
| 2025-08-21 00:16:07 - INFO - [e4056e7f-abce-447f-9556-fc5a853b32aa] 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_045.mp4' | |
| 2025-08-21 00:16:07 - INFO - [e4056e7f-abce-447f-9556-fc5a853b32aa] Video saved to temporary file: temp_videos/e4056e7f-abce-447f-9556-fc5a853b32aa.mp4 | |
| 2025-08-21 00:16:07 - INFO - [e4056e7f-abce-447f-9556-fc5a853b32aa] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:16:12 - INFO - [e4056e7f-abce-447f-9556-fc5a853b32aa] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:16:12 - INFO - [e4056e7f-abce-447f-9556-fc5a853b32aa] 30 frames saved to temp_videos/e4056e7f-abce-447f-9556-fc5a853b32aa | |
| 2025-08-21 00:16:25 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:16:39 - INFO - Tokens per second: 7.282653773730579, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:16:39 - INFO - [e4056e7f-abce-447f-9556-fc5a853b32aa] Inference time: 31.87 seconds, CPU usage: 36.1%, CPU core utilization: [40.4, 17.4, 32.9, 53.5] | |
| 2025-08-21 00:16:39 - INFO - [e4056e7f-abce-447f-9556-fc5a853b32aa] Cleaned up temporary frame directory: temp_videos/e4056e7f-abce-447f-9556-fc5a853b32aa | |
| 2025-08-21 00:16:39 - INFO - [5d08d2de-911a-498a-9b3a-f89597376f02] 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_046.mp4' | |
| 2025-08-21 00:16:39 - INFO - [5d08d2de-911a-498a-9b3a-f89597376f02] Video saved to temporary file: temp_videos/5d08d2de-911a-498a-9b3a-f89597376f02.mp4 | |
| 2025-08-21 00:16:39 - INFO - [5d08d2de-911a-498a-9b3a-f89597376f02] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:16:44 - INFO - [5d08d2de-911a-498a-9b3a-f89597376f02] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:16:44 - INFO - [5d08d2de-911a-498a-9b3a-f89597376f02] 30 frames saved to temp_videos/5d08d2de-911a-498a-9b3a-f89597376f02 | |
| 2025-08-21 00:16:57 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:17:11 - INFO - Tokens per second: 7.413608779975096, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:17:11 - INFO - [5d08d2de-911a-498a-9b3a-f89597376f02] Inference time: 32.04 seconds, CPU usage: 36.2%, CPU core utilization: [15.1, 15.9, 55.1, 58.5] | |
| 2025-08-21 00:17:11 - INFO - [5d08d2de-911a-498a-9b3a-f89597376f02] Cleaned up temporary frame directory: temp_videos/5d08d2de-911a-498a-9b3a-f89597376f02 | |
| 2025-08-21 00:17:11 - INFO - [72154fe0-fabb-4695-a74c-07b13b4d70ee] 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_047.mp4' | |
| 2025-08-21 00:17:11 - INFO - [72154fe0-fabb-4695-a74c-07b13b4d70ee] Video saved to temporary file: temp_videos/72154fe0-fabb-4695-a74c-07b13b4d70ee.mp4 | |
| 2025-08-21 00:17:11 - INFO - [72154fe0-fabb-4695-a74c-07b13b4d70ee] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:17:16 - INFO - [72154fe0-fabb-4695-a74c-07b13b4d70ee] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:17:16 - INFO - [72154fe0-fabb-4695-a74c-07b13b4d70ee] 30 frames saved to temp_videos/72154fe0-fabb-4695-a74c-07b13b4d70ee | |
| 2025-08-21 00:17:29 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:17:52 - INFO - Tokens per second: 9.744964420585076, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:17:52 - INFO - [72154fe0-fabb-4695-a74c-07b13b4d70ee] Inference time: 40.16 seconds, CPU usage: 34.8%, CPU core utilization: [16.9, 39.2, 15.3, 67.8] | |
| 2025-08-21 00:17:52 - INFO - [72154fe0-fabb-4695-a74c-07b13b4d70ee] Cleaned up temporary frame directory: temp_videos/72154fe0-fabb-4695-a74c-07b13b4d70ee | |
| 2025-08-21 00:17:52 - INFO - [66d33b91-3d66-4c03-8dce-a78ba0c64f20] 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_048.mp4' | |
| 2025-08-21 00:17:52 - INFO - [66d33b91-3d66-4c03-8dce-a78ba0c64f20] Video saved to temporary file: temp_videos/66d33b91-3d66-4c03-8dce-a78ba0c64f20.mp4 | |
| 2025-08-21 00:17:52 - INFO - [66d33b91-3d66-4c03-8dce-a78ba0c64f20] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:17:56 - INFO - [66d33b91-3d66-4c03-8dce-a78ba0c64f20] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:17:56 - INFO - [66d33b91-3d66-4c03-8dce-a78ba0c64f20] 30 frames saved to temp_videos/66d33b91-3d66-4c03-8dce-a78ba0c64f20 | |
| 2025-08-21 00:18:09 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:18:21 - INFO - Tokens per second: 5.534022820709767, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:18:21 - INFO - [66d33b91-3d66-4c03-8dce-a78ba0c64f20] Inference time: 28.96 seconds, CPU usage: 36.9%, CPU core utilization: [64.7, 22.2, 29.9, 30.5] | |
| 2025-08-21 00:18:21 - INFO - [66d33b91-3d66-4c03-8dce-a78ba0c64f20] Cleaned up temporary frame directory: temp_videos/66d33b91-3d66-4c03-8dce-a78ba0c64f20 | |
| 2025-08-21 00:18:21 - INFO - [f92833f5-5c53-4d98-bf8a-1686007f24e8] 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_049.mp4' | |
| 2025-08-21 00:18:21 - INFO - [f92833f5-5c53-4d98-bf8a-1686007f24e8] Video saved to temporary file: temp_videos/f92833f5-5c53-4d98-bf8a-1686007f24e8.mp4 | |
| 2025-08-21 00:18:21 - INFO - [f92833f5-5c53-4d98-bf8a-1686007f24e8] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:18:25 - INFO - [f92833f5-5c53-4d98-bf8a-1686007f24e8] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:18:25 - INFO - [f92833f5-5c53-4d98-bf8a-1686007f24e8] 30 frames saved to temp_videos/f92833f5-5c53-4d98-bf8a-1686007f24e8 | |
| 2025-08-21 00:18:38 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:18:51 - INFO - Tokens per second: 6.507467905304537, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:18:51 - INFO - [f92833f5-5c53-4d98-bf8a-1686007f24e8] Inference time: 30.29 seconds, CPU usage: 36.6%, CPU core utilization: [53.7, 28.6, 33.4, 30.8] | |
| 2025-08-21 00:18:51 - INFO - [f92833f5-5c53-4d98-bf8a-1686007f24e8] Cleaned up temporary frame directory: temp_videos/f92833f5-5c53-4d98-bf8a-1686007f24e8 | |
| 2025-08-21 00:18:51 - INFO - [08e97c3f-0eee-4b5d-a9f5-51984817e6f9] 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_050.mp4' | |
| 2025-08-21 00:18:51 - INFO - [08e97c3f-0eee-4b5d-a9f5-51984817e6f9] Video saved to temporary file: temp_videos/08e97c3f-0eee-4b5d-a9f5-51984817e6f9.mp4 | |
| 2025-08-21 00:18:51 - INFO - [08e97c3f-0eee-4b5d-a9f5-51984817e6f9] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:18:56 - INFO - [08e97c3f-0eee-4b5d-a9f5-51984817e6f9] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:18:56 - INFO - [08e97c3f-0eee-4b5d-a9f5-51984817e6f9] 30 frames saved to temp_videos/08e97c3f-0eee-4b5d-a9f5-51984817e6f9 | |
| 2025-08-21 00:19:09 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:19:18 - INFO - Tokens per second: 3.2541179562626197, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:19:18 - INFO - [08e97c3f-0eee-4b5d-a9f5-51984817e6f9] Inference time: 26.65 seconds, CPU usage: 37.9%, CPU core utilization: [48.0, 17.9, 20.3, 65.1] | |
| 2025-08-21 00:19:18 - INFO - [08e97c3f-0eee-4b5d-a9f5-51984817e6f9] Cleaned up temporary frame directory: temp_videos/08e97c3f-0eee-4b5d-a9f5-51984817e6f9 | |
| 2025-08-21 00:19:18 - INFO - [fa21ed16-4a4b-4252-a232-b1be5c853f7d] 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_051.mp4' | |
| 2025-08-21 00:19:18 - INFO - [fa21ed16-4a4b-4252-a232-b1be5c853f7d] Video saved to temporary file: temp_videos/fa21ed16-4a4b-4252-a232-b1be5c853f7d.mp4 | |
| 2025-08-21 00:19:18 - INFO - [fa21ed16-4a4b-4252-a232-b1be5c853f7d] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:19:22 - INFO - [fa21ed16-4a4b-4252-a232-b1be5c853f7d] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:19:22 - INFO - [fa21ed16-4a4b-4252-a232-b1be5c853f7d] 30 frames saved to temp_videos/fa21ed16-4a4b-4252-a232-b1be5c853f7d | |
| 2025-08-21 00:19:35 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:19:45 - INFO - Tokens per second: 3.912398850108666, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:19:45 - INFO - [fa21ed16-4a4b-4252-a232-b1be5c853f7d] Inference time: 27.18 seconds, CPU usage: 37.2%, CPU core utilization: [62.7, 17.9, 17.4, 50.5] | |
| 2025-08-21 00:19:45 - INFO - [fa21ed16-4a4b-4252-a232-b1be5c853f7d] Cleaned up temporary frame directory: temp_videos/fa21ed16-4a4b-4252-a232-b1be5c853f7d | |
| 2025-08-21 00:19:45 - INFO - [5e7d1173-00c2-46a2-81a0-1dc1223bd7c2] 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_052.mp4' | |
| 2025-08-21 00:19:45 - INFO - [5e7d1173-00c2-46a2-81a0-1dc1223bd7c2] Video saved to temporary file: temp_videos/5e7d1173-00c2-46a2-81a0-1dc1223bd7c2.mp4 | |
| 2025-08-21 00:19:45 - INFO - [5e7d1173-00c2-46a2-81a0-1dc1223bd7c2] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:19:50 - INFO - [5e7d1173-00c2-46a2-81a0-1dc1223bd7c2] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:19:50 - INFO - [5e7d1173-00c2-46a2-81a0-1dc1223bd7c2] 30 frames saved to temp_videos/5e7d1173-00c2-46a2-81a0-1dc1223bd7c2 | |
| 2025-08-21 00:20:02 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:20:16 - INFO - Tokens per second: 7.248168780638238, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:20:16 - INFO - [5e7d1173-00c2-46a2-81a0-1dc1223bd7c2] Inference time: 31.69 seconds, CPU usage: 36.1%, CPU core utilization: [60.1, 41.3, 16.2, 26.8] | |
| 2025-08-21 00:20:16 - INFO - [5e7d1173-00c2-46a2-81a0-1dc1223bd7c2] Cleaned up temporary frame directory: temp_videos/5e7d1173-00c2-46a2-81a0-1dc1223bd7c2 | |
| 2025-08-21 00:20:16 - INFO - [1456aa86-ac67-48b3-8739-8f5901221155] 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_053.mp4' | |
| 2025-08-21 00:20:16 - INFO - [1456aa86-ac67-48b3-8739-8f5901221155] Video saved to temporary file: temp_videos/1456aa86-ac67-48b3-8739-8f5901221155.mp4 | |
| 2025-08-21 00:20:16 - INFO - [1456aa86-ac67-48b3-8739-8f5901221155] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:20:21 - INFO - [1456aa86-ac67-48b3-8739-8f5901221155] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:20:21 - INFO - [1456aa86-ac67-48b3-8739-8f5901221155] 30 frames saved to temp_videos/1456aa86-ac67-48b3-8739-8f5901221155 | |
| 2025-08-21 00:20:34 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:20:47 - INFO - Tokens per second: 6.420566489349132, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:20:47 - INFO - [1456aa86-ac67-48b3-8739-8f5901221155] Inference time: 30.22 seconds, CPU usage: 36.5%, CPU core utilization: [46.5, 21.6, 59.6, 18.1] | |
| 2025-08-21 00:20:47 - INFO - [1456aa86-ac67-48b3-8739-8f5901221155] Cleaned up temporary frame directory: temp_videos/1456aa86-ac67-48b3-8739-8f5901221155 | |
| 2025-08-21 00:20:47 - INFO - [b6dffc6c-f438-4737-809c-69a392f5e9c0] 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_054.mp4' | |
| 2025-08-21 00:20:47 - INFO - [b6dffc6c-f438-4737-809c-69a392f5e9c0] Video saved to temporary file: temp_videos/b6dffc6c-f438-4737-809c-69a392f5e9c0.mp4 | |
| 2025-08-21 00:20:47 - INFO - [b6dffc6c-f438-4737-809c-69a392f5e9c0] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:20:51 - INFO - [b6dffc6c-f438-4737-809c-69a392f5e9c0] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:20:51 - INFO - [b6dffc6c-f438-4737-809c-69a392f5e9c0] 30 frames saved to temp_videos/b6dffc6c-f438-4737-809c-69a392f5e9c0 | |
| 2025-08-21 00:21:04 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:21:15 - INFO - Tokens per second: 5.19902103533599, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:21:15 - INFO - [b6dffc6c-f438-4737-809c-69a392f5e9c0] Inference time: 28.49 seconds, CPU usage: 37.6%, CPU core utilization: [49.0, 34.0, 48.4, 19.0] | |
| 2025-08-21 00:21:15 - INFO - [b6dffc6c-f438-4737-809c-69a392f5e9c0] Cleaned up temporary frame directory: temp_videos/b6dffc6c-f438-4737-809c-69a392f5e9c0 | |
| 2025-08-21 00:21:15 - INFO - [41c34e88-b17f-4653-a2d5-652b09643d82] 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_055.mp4' | |
| 2025-08-21 00:21:15 - INFO - [41c34e88-b17f-4653-a2d5-652b09643d82] Video saved to temporary file: temp_videos/41c34e88-b17f-4653-a2d5-652b09643d82.mp4 | |
| 2025-08-21 00:21:15 - INFO - [41c34e88-b17f-4653-a2d5-652b09643d82] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:21:20 - INFO - [41c34e88-b17f-4653-a2d5-652b09643d82] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:21:20 - INFO - [41c34e88-b17f-4653-a2d5-652b09643d82] 30 frames saved to temp_videos/41c34e88-b17f-4653-a2d5-652b09643d82 | |
| 2025-08-21 00:21:33 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:21:46 - INFO - Tokens per second: 6.72473013041542, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:21:46 - INFO - [41c34e88-b17f-4653-a2d5-652b09643d82] Inference time: 30.70 seconds, CPU usage: 36.5%, CPU core utilization: [35.2, 45.0, 37.4, 28.4] | |
| 2025-08-21 00:21:46 - INFO - [41c34e88-b17f-4653-a2d5-652b09643d82] Cleaned up temporary frame directory: temp_videos/41c34e88-b17f-4653-a2d5-652b09643d82 | |
| 2025-08-21 00:21:46 - INFO - [1d8dced7-a51d-4146-b969-9cf087ebf060] 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_056.mp4' | |
| 2025-08-21 00:21:46 - INFO - [1d8dced7-a51d-4146-b969-9cf087ebf060] Video saved to temporary file: temp_videos/1d8dced7-a51d-4146-b969-9cf087ebf060.mp4 | |
| 2025-08-21 00:21:46 - INFO - [1d8dced7-a51d-4146-b969-9cf087ebf060] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:21:51 - INFO - [1d8dced7-a51d-4146-b969-9cf087ebf060] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:21:51 - INFO - [1d8dced7-a51d-4146-b969-9cf087ebf060] 30 frames saved to temp_videos/1d8dced7-a51d-4146-b969-9cf087ebf060 | |
| 2025-08-21 00:22:04 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:22:15 - INFO - Tokens per second: 5.483718629411901, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:22:15 - INFO - [1d8dced7-a51d-4146-b969-9cf087ebf060] Inference time: 28.89 seconds, CPU usage: 37.1%, CPU core utilization: [27.1, 19.3, 43.8, 58.1] | |
| 2025-08-21 00:22:15 - INFO - [1d8dced7-a51d-4146-b969-9cf087ebf060] Cleaned up temporary frame directory: temp_videos/1d8dced7-a51d-4146-b969-9cf087ebf060 | |
| 2025-08-21 00:22:15 - INFO - [ccc3c8c3-225b-4c96-acfe-9c195f572e4a] 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_057.mp4' | |
| 2025-08-21 00:22:15 - INFO - [ccc3c8c3-225b-4c96-acfe-9c195f572e4a] Video saved to temporary file: temp_videos/ccc3c8c3-225b-4c96-acfe-9c195f572e4a.mp4 | |
| 2025-08-21 00:22:15 - INFO - [ccc3c8c3-225b-4c96-acfe-9c195f572e4a] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-21 00:22:20 - INFO - [ccc3c8c3-225b-4c96-acfe-9c195f572e4a] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-21 00:22:20 - INFO - [ccc3c8c3-225b-4c96-acfe-9c195f572e4a] 30 frames saved to temp_videos/ccc3c8c3-225b-4c96-acfe-9c195f572e4a | |
| 2025-08-21 00:22:33 - INFO - vision_config is None, using default vision config | |
| 2025-08-21 00:22:49 - INFO - Tokens per second: 8.073006063593622, Peak GPU memory MB: 11824.375 | |
| 2025-08-21 00:22:49 - INFO - [ccc3c8c3-225b-4c96-acfe-9c195f572e4a] Inference time: 33.72 seconds, CPU usage: 35.9%, CPU core utilization: [27.8, 59.7, 19.4, 37.0] | |
| 2025-08-21 00:22:49 - INFO - [ccc3c8c3-225b-4c96-acfe-9c195f572e4a] Cleaned up temporary frame directory: temp_videos/ccc3c8c3-225b-4c96-acfe-9c195f572e4a | |