2024-07-11 22:15:24 | INFO | model_worker | args: Namespace(host='0.0.0.0', port=40006, worker_address='http://10.140.60.25:40006', controller_address='http://10.140.60.209:10075', model_path='share_internvl/InternVL2-40B/', model_name=None, device='auto', limit_model_concurrency=5, stream_interval=1, load_8bit=False)
2024-07-11 22:15:24 | INFO | model_worker | Loading the model InternVL2-40B on worker 1380b0 ...
2024-07-11 22:15:24 | WARNING | transformers.tokenization_utils_base | Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
2024-07-11 22:15:24 | WARNING | transformers.tokenization_utils_base | Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
2024-07-11 22:15:30 | ERROR | stderr | /mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:397: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `None` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`. This was detected when initializing the generation config instance, which means the corresponding file may hold incorrect parameterization and should be fixed.
2024-07-11 22:15:30 | ERROR | stderr |   warnings.warn(
2024-07-11 22:15:33 | ERROR | stderr | 
Loading checkpoint shards:   0%|          | 0/17 [00:00<?, ?it/s]
2024-07-11 22:15:35 | ERROR | stderr | 
Loading checkpoint shards:   6%|▌         | 1/17 [00:02<00:33,  2.09s/it]
2024-07-11 22:15:37 | ERROR | stderr | 
Loading checkpoint shards:  12%|█▏        | 2/17 [00:04<00:30,  2.03s/it]
2024-07-11 22:15:39 | ERROR | stderr | 
Loading checkpoint shards:  18%|█▊        | 3/17 [00:06<00:28,  2.02s/it]
2024-07-11 22:15:41 | ERROR | stderr | 
Loading checkpoint shards:  24%|██▎       | 4/17 [00:08<00:26,  2.04s/it]
2024-07-11 22:15:43 | ERROR | stderr | 
Loading checkpoint shards:  29%|██▉       | 5/17 [00:10<00:24,  2.06s/it]
2024-07-11 22:15:45 | ERROR | stderr | 
Loading checkpoint shards:  35%|███▌      | 6/17 [00:12<00:22,  2.09s/it]
2024-07-11 22:15:47 | ERROR | stderr | 
Loading checkpoint shards:  41%|████      | 7/17 [00:14<00:21,  2.12s/it]
2024-07-11 22:15:49 | ERROR | stderr | 
Loading checkpoint shards:  47%|████▋     | 8/17 [00:16<00:19,  2.18s/it]
2024-07-11 22:15:51 | ERROR | stderr | 
Loading checkpoint shards:  53%|█████▎    | 9/17 [00:18<00:16,  2.11s/it]
2024-07-11 22:15:53 | ERROR | stderr | 
Loading checkpoint shards:  59%|█████▉    | 10/17 [00:20<00:14,  2.05s/it]
2024-07-11 22:15:55 | ERROR | stderr | 
Loading checkpoint shards:  65%|██████▍   | 11/17 [00:22<00:12,  2.09s/it]
2024-07-11 22:15:58 | ERROR | stderr | 
Loading checkpoint shards:  71%|███████   | 12/17 [00:25<00:10,  2.12s/it]
2024-07-11 22:16:00 | ERROR | stderr | 
Loading checkpoint shards:  76%|███████▋  | 13/17 [00:27<00:08,  2.14s/it]
2024-07-11 22:16:02 | ERROR | stderr | 
Loading checkpoint shards:  82%|████████▏ | 14/17 [00:29<00:06,  2.22s/it]
2024-07-11 22:16:04 | ERROR | stderr | 
Loading checkpoint shards:  88%|████████▊ | 15/17 [00:31<00:04,  2.19s/it]
2024-07-11 22:16:07 | ERROR | stderr | 
Loading checkpoint shards:  94%|█████████▍| 16/17 [00:33<00:02,  2.18s/it]
2024-07-11 22:16:08 | ERROR | stderr | 
Loading checkpoint shards: 100%|██████████| 17/17 [00:35<00:00,  1.89s/it]
2024-07-11 22:16:08 | ERROR | stderr | 
Loading checkpoint shards: 100%|██████████| 17/17 [00:35<00:00,  2.07s/it]
2024-07-11 22:16:08 | ERROR | stderr | 
2024-07-11 22:16:08 | INFO | model_worker | Register to controller
2024-07-11 22:16:08 | ERROR | stderr | INFO:     Started server process [50195]
2024-07-11 22:16:08 | ERROR | stderr | INFO:     Waiting for application startup.
2024-07-11 22:16:08 | ERROR | stderr | INFO:     Application startup complete.
2024-07-11 22:16:08 | ERROR | stderr | INFO:     Uvicorn running on http://0.0.0.0:40006 (Press CTRL+C to quit)
2024-07-11 22:16:23 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:16:38 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:16:53 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:17:08 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:17:23 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:17:38 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:17:49 | INFO | stdout | INFO:     10.140.60.209:42548 - "POST /worker_get_status HTTP/1.1" 200 OK
2024-07-11 22:17:53 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:18:08 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:18:08 | ERROR | model_worker | heart beat error: HTTPConnectionPool(host='10.140.60.209', port=10075): Max retries exceeded with url: /receive_heart_beat (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f60a42b60e0>: Failed to establish a new connection: [Errno 111] Connection refused'))
2024-07-11 22:18:13 | INFO | model_worker | Register to controller
2024-07-11 22:18:17 | INFO | stdout | INFO:     10.140.60.209:42746 - "POST /worker_get_status HTTP/1.1" 200 OK
2024-07-11 22:18:21 | INFO | stdout | INFO:     10.140.60.209:42872 - "POST /worker_get_status HTTP/1.1" 200 OK
2024-07-11 22:18:22 | INFO | stdout | INFO:     10.140.60.209:42892 - "POST /worker_get_status HTTP/1.1" 200 OK
2024-07-11 22:18:22 | INFO | stdout | INFO:     10.140.60.209:42912 - "POST /worker_get_status HTTP/1.1" 200 OK
2024-07-11 22:18:28 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:18:43 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:18:58 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:19:13 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:19:28 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:19:32 | INFO | stdout | INFO:     10.140.60.209:43356 - "POST /worker_get_status HTTP/1.1" 200 OK
2024-07-11 22:19:32 | INFO | stdout | INFO:     10.140.60.209:43372 - "POST /worker_get_status HTTP/1.1" 200 OK
2024-07-11 22:19:43 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:19:58 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: None. global_counter: 0
2024-07-11 22:19:59 | INFO | stdout | INFO:     10.140.60.209:43468 - "POST /worker_get_status HTTP/1.1" 200 OK
2024-07-11 22:19:59 | INFO | stdout | INFO:     10.140.60.209:43487 - "POST /worker_get_status HTTP/1.1" 200 OK
2024-07-11 22:20:00 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=4, locked=False). global_counter: 1
2024-07-11 22:20:00 | INFO | stdout | INFO:     10.140.60.209:43492 - "POST /worker_generate_stream HTTP/1.1" 200 OK
2024-07-11 22:20:00 | INFO | model_worker | max_input_tile_list: [12]
2024-07-11 22:20:00 | INFO | model_worker | Split images to torch.Size([13, 3, 448, 448])
2024-07-11 22:20:00 | INFO | model_worker | []
2024-07-11 22:20:00 | INFO | model_worker | Generation config: {'num_beams': 1, 'max_new_tokens': 2048, 'do_sample': True, 'temperature': 0.8, 'repetition_penalty': 1.1, 'max_length': 8192, 'top_p': 0.7, 'streamer': <transformers.generation.streamers.TextIteratorStreamer object at 0x7f60a430a050>}
2024-07-11 22:20:02 | WARNING | transformers.generation.utils | Both `max_new_tokens` (=2048) and `max_length`(=8192) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)
2024-07-11 22:20:05 | ERROR | stderr | Exception in thread Thread-3 (chat):
2024-07-11 22:20:05 | ERROR | stderr | Traceback (most recent call last):
2024-07-11 22:20:05 | ERROR | stderr |   File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/threading.py", line 1009, in _bootstrap_inner
2024-07-11 22:20:05 | ERROR | stderr |     self.run()
2024-07-11 22:20:05 | ERROR | stderr |   File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/threading.py", line 946, in run
2024-07-11 22:20:05 | ERROR | stderr |     self._target(*self._args, **self._kwargs)
2024-07-11 22:20:05 | ERROR | stderr |   File "/mnt/petrelfs/wangweiyun/.cache/huggingface/modules/transformers_modules/InternVL2-40B/modeling_internvl_chat.py", line 280, in chat
2024-07-11 22:20:05 | ERROR | stderr |     generation_output = self.generate(
2024-07-11 22:20:05 | ERROR | stderr |   File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
2024-07-11 22:20:05 | ERROR | stderr |     return func(*args, **kwargs)
2024-07-11 22:20:05 | ERROR | stderr |   File "/mnt/petrelfs/wangweiyun/.cache/huggingface/modules/transformers_modules/InternVL2-40B/modeling_internvl_chat.py", line 330, in generate
2024-07-11 22:20:05 | ERROR | stderr |     outputs = self.language_model.generate(
2024-07-11 22:20:05 | ERROR | stderr |   File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
2024-07-11 22:20:05 | ERROR | stderr |     return func(*args, **kwargs)
2024-07-11 22:20:05 | ERROR | stderr |   File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/utils.py", line 1525, in generate
2024-07-11 22:20:05 | ERROR | stderr |     return self.sample(
2024-07-11 22:20:05 | ERROR | stderr |   File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/utils.py", line 2641, in sample
2024-07-11 22:20:05 | ERROR | stderr |     next_token_scores = logits_processor(input_ids, next_token_logits)
2024-07-11 22:20:05 | ERROR | stderr |   File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/logits_process.py", line 97, in __call__
2024-07-11 22:20:05 | ERROR | stderr |     scores = processor(input_ids, scores)
2024-07-11 22:20:05 | ERROR | stderr |   File "/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/logits_process.py", line 333, in __call__
2024-07-11 22:20:05 | ERROR | stderr |     score = torch.gather(scores, 1, input_ids)
2024-07-11 22:20:05 | ERROR | stderr | RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:2 and cuda:0! (when checking argument for argument index in method wrapper_CUDA_gather)
2024-07-11 22:20:10 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:20:13 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:20:28 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:20:43 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:20:58 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:21:13 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:21:29 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:21:44 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:21:59 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:22:14 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:22:29 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:22:44 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:22:59 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:23:14 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:23:29 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:23:44 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:23:59 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:24:14 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:24:29 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:24:44 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:24:59 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:25:14 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:25:29 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:25:44 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:25:59 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:26:14 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:26:29 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1
2024-07-11 22:26:44 | INFO | model_worker | Send heart beat. Models: ['InternVL2-40B']. Semaphore: Semaphore(value=5, locked=False). global_counter: 1