runtime error

Exit code: 1. Reason: �██| 4/4 [00:01<00:00, 3.61it/s] Loading pipeline components...: 100%|██████████| 4/4 [00:01<00:00, 3.61it/s] Attention backends are an experimental feature and the API may be subject to change. __init__.py: 0%| | 0.00/387 [00:00<?, ?B/s] __init__.py: 100%|██████████| 387/387 [00:00<00:00, 4.93MB/s] build/torch28-cxx11-cu128-x86_64-linux/_(…): 0%| | 0.00/804M [00:00<?, ?B/s] build/torch28-cxx11-cu128-x86_64-linux/_(…): 12%|█▏ | 99.3M/804M [00:01<00:07, 95.1MB/s] build/torch28-cxx11-cu128-x86_64-linux/_(…): 100%|██████████| 804M/804M [00:01<00:00, 716MB/s] _ops.py: 0%| | 0.00/218 [00:00<?, ?B/s] _ops.py: 100%|██████████| 218/218 [00:00<00:00, 1.95MB/s] __init__.py: 0%| | 0.00/1.03k [00:00<?, ?B/s] __init__.py: 100%|██████████| 1.03k/1.03k [00:00<00:00, 12.2MB/s] flash_attn_interface.py: 0%| | 0.00/41.0k [00:00<?, ?B/s] flash_attn_interface.py: 100%|██████████| 41.0k/41.0k [00:00<00:00, 217MB/s] metadata.json: 0%| | 0.00/21.0 [00:00<?, ?B/s] metadata.json: 100%|██████████| 21.0/21.0 [00:00<00:00, 309kB/s] Loaded as API: https://huggingface.co/proxy/multimodalart-mistral-text-encoder.hf.space ✔ Traceback (most recent call last): File "/home/user/app/app.py", line 85, in <module> optimize_pipeline_( File "/home/user/app/optimization.py", line 74, in optimize_pipeline_ archive_file = compile_block(blocks_kind) File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 190, in gradio_handler schedule_response = client.schedule(task_id=task_id, request=request, duration=duration_, gpu_size=gpu_size) File "/usr/local/lib/python3.10/site-packages/spaces/zero/client.py", line 152, in schedule raise error("ZeroGPU illegal duration", message) gradio.exceptions.Error: 'The requested GPU duration (1200s) is larger than the maximum allowed'

Container logs: