runtime error

Exit code: 1. Reason: ment already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/site-packages (from jinja2->torch->bitsandbytes->-r requirements.txt (line 5)) (2.1.5) [notice] A new release of pip available: 22.3.1 -> 24.3.1 [notice] To update, run: pip install --upgrade pip Running main script... Traceback (most recent call last): File "/home/user/app/main_gr.py", line 144, in <module> demo = create_demo(args.config) ^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/user/app/main_gr.py", line 12, in create_demo generator = FluxPipeline.load_pipeline_from_config_path(config_path) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/user/app/flux_pipeline.py", line 679, in load_pipeline_from_config_path return cls.load_pipeline_from_config(config, debug=debug) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/user/app/flux_pipeline.py", line 693, in load_pipeline_from_config models = load_models_from_config(config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/user/app/util.py", line 326, in load_models_from_config clip, t5 = load_text_encoders(config) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/user/app/util.py", line 260, in load_text_encoders clip = HFEmbedder( ^^^^^^^^^^^ File "/home/user/app/modules/conditioner.py", line 56, in __init__ device if isinstance(device, torch.device) else torch.device(device) ^^^^^^^^^^^^^^^^^^^^ RuntimeError: Cannot access accelerator device when none is available. Traceback (most recent call last): File "/home/user/app/setup.py", line 81, in <module> run_main() File "/home/user/app/setup.py", line 73, in run_main subprocess.run([sys.executable, "main_gr.py"], check=True) File "/usr/local/lib/python3.11/subprocess.py", line 571, in run raise CalledProcessError(retcode, process.args, subprocess.CalledProcessError: Command '['/usr/local/bin/python', 'main_gr.py']' returned non-zero exit status 1.

Container logs: