2025-07-02T12:19:45.
310174785Z ==========
2025-07-02T12:19:45.310177248Z == CUDA ==
2025-07-02T12:19:45.310206803Z ==========
2025-07-02T12:19:45.312354979Z CUDA Version 12.1.1
2025-07-02T12:19:45.313361291Z Container image Copyright (c) 2016-2023, NVIDIA
CORPORATION & AFFILIATES. All rights reserved.
2025-07-02T12:19:45.314151951Z This container image and its contents are governed
by the NVIDIA Deep Learning Container License.
2025-07-02T12:19:45.314154024Z By pulling and using the container, you accept the
terms and conditions of this license:
2025-07-02T12:19:45.314155456Z https://developer.nvidia.com/ngc/nvidia-deep-
learning-container-license
2025-07-02T12:19:45.314158691Z A copy of this license is made available in this
container at /NGC-DL-CONTAINER-LICENSE for your convenience.
2025-07-02T12:19:45.340323224Z --- GENERIC VISION HANDLER START ---
2025-07-02T12:19:46.922077830Z --- runpod imported ---
2025-07-02T12:19:48.019176859Z --- torch imported ---
2025-07-02T12:19:48.150776833Z
/usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py:111:
FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5
of Transformers. Use `HF_HOME` instead.
2025-07-02T12:19:48.150808099Z warnings.warn(
2025-07-02T12:19:48.857756427Z --- transformers parts imported ---
2025-07-02T12:19:48.858179218Z vision_process.py :42 2025-07-02 12:19:48,857
set VIDEO_TOTAL_PIXELS: 90316800
2025-07-02T12:19:48.858186529Z --- qwen_vl_utils imported ---
2025-07-02T12:19:48.858191025Z --- All primary imports complete ---
2025-07-02T12:19:48.858192508Z Loading quantization_config...
2025-07-02T12:19:48.858442250Z Loading model: Qwen/Qwen2-VL-7B-Instruct...
2025-07-02T12:20:34.268409282Z
Fetching 5 files: 0%| | 0/5 [00:00<?, ?it/s]
Fetching 5 files: 20%|██ | 1/5 [00:36<02:24, 36.08s/it]
Fetching 5 files: 40%|████ | 2/5 [00:43<00:57, 19.12s/it]
Fetching 5 files: 100%|██████████| 5/5 [00:43<00:00, 8.67s/it]
2025-07-02T12:20:34.544610665Z modeling.py :991 2025-07-02 12:20:34,544 We
will use 90% of the memory on device 0 for storing the model, and 10% for the
buffer to avoid OOM. You can set `max_memory` in to a higher value to use more
memory (at your own risk).
2025-07-02T12:20:46.037750174Z
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 20%|██ | 1/5 [00:02<00:09, 2.35s/it]
Loading checkpoint shards: 40%|████ | 2/5 [00:05<00:07, 2.55s/it]
Loading checkpoint shards: 60%|██████ | 3/5 [00:08<00:05, 2.75s/it]
Loading checkpoint shards: 80%|████████ | 4/5 [00:11<00:02, 2.87s/it]
Loading checkpoint shards: 100%|██████████| 5/5 [00:11<00:00, 1.96s/it]
Loading checkpoint shards: 100%|██████████| 5/5 [00:11<00:00, 2.29s/it]
2025-07-02T12:20:46.749634268Z Loading processor...
2025-07-02T12:20:47.772981697Z Using a slow image processor as `use_fast` is unset
and a slow processor was saved with this model. `use_fast=True` will be the default
behavior in v4.52, even if the model was saved with a slow processor. This will
result in minor differences in outputs. You'll still be able to use a slow
processor with `use_fast=False`.
2025-07-02T12:20:51.238678900Z You have video processor config saved in
`preprocessor.json` file which is deprecated. Video processor configs should be
saved in their own `video_preprocessor.json` file. You can rename the file or load
and save the processor back which renames it automatically. Loading from
`preprocessor.json` will be removed in v5.0.
2025-07-02T12:20:52.480806265Z --- Model and Processor Loaded Successfully ---
2025-07-02T12:20:52.480851232Z --- Starting RunPod serverless handler ---
2025-07-02T12:20:52.480859645Z --- Starting Serverless Worker | Version 1.7.12 ---
2025-07-02T12:20:53.087850207Z {"requestId": null, "message": "Jobs in queue: 1",
"level": "INFO"}
2025-07-02T12:20:53.087871228Z {"requestId": null, "message": "Jobs in progress:
1", "level": "INFO"}
2025-07-02T12:20:53.088215132Z {"requestId": "7d6e6d59-356e-49dd-8daa-7d4dadc18631-
e2", "message": "Started.", "level": "INFO"}
2025-07-02T12:20:53.088234601Z --- Job Received --- Job ID: 7d6e6d59-356e-49dd-
8daa-7d4dadc18631-e2
2025-07-02T12:20:53.088239658Z Processing 1 image(s) with prompt...
2025-07-02T12:20:53.088243574Z Decoding base64 image...
2025-07-02T12:20:53.112250466Z Image loaded successfully: (900, 1600)
2025-07-02T12:20:53.112281413Z --- Starting image analysis with prompt (length:
2214) ---
2025-07-02T12:20:53.112285529Z Preparing inputs for the model...
2025-07-02T12:20:53.227225997Z Generating response from the model...
2025-07-02T12:20:57.209301496Z Model response generated successfully (length: 2751)
2025-07-02T12:20:57.269171847Z {"requestId": "7d6e6d59-356e-49dd-8daa-7d4dadc18631-
e2", "message": "Finished.", "level": "INFO"}
2025-07-02T12:20:58.947733846Z {"requestId": null, "message": "Jobs in queue: 1",
"level": "INFO"}
2025-07-02T12:20:58.947753556Z {"requestId": null, "message": "Jobs in progress:
1", "level": "INFO"}
2025-07-02T12:20:58.947758113Z {"requestId": "5d03854a-4291-4f60-a46c-1cdbc64ccb05-
e1", "message": "Started.", "level": "INFO"}
2025-07-02T12:20:58.947761838Z --- Job Received --- Job ID: 5d03854a-4291-4f60-
a46c-1cdbc64ccb05-e1
2025-07-02T12:20:58.947765243Z Processing 1 image(s) with prompt...
2025-07-02T12:20:58.947768738Z Decoding base64 image...
2025-07-02T12:20:58.953663567Z Image loaded successfully: (1280, 960)
2025-07-02T12:20:58.953679831Z --- Starting image analysis with prompt (length:
2234) ---
2025-07-02T12:20:58.953684478Z Preparing inputs for the model...
2025-07-02T12:20:59.023109320Z Generating response from the model...
2025-07-02T12:21:01.960272584Z Model response generated successfully (length: 2777)
2025-07-02T12:21:02.031091086Z {"requestId": "5d03854a-4291-4f60-a46c-1cdbc64ccb05-
e1", "message": "Finished.", "level": "INFO"}
