runtime error

Exit code: 1. Reason: mponents...: 60%|██████ | 3/5 [00:06<00:03, 1.88s/it] Loading pipeline components...: 100%|██████████| 5/5 [00:06<00:00, 1.32s/it] Qwen-Image-2512-Lightning-4steps-V1.0-bf(…): 0%| | 0.00/850M [00:00<?, ?B/s] Qwen-Image-2512-Lightning-4steps-V1.0-bf(…): 8%|▊ | 68.6M/850M [00:01<00:13, 57.1MB/s] Qwen-Image-2512-Lightning-4steps-V1.0-bf(…): 100%|██████████| 850M/850M [00:01<00:00, 499MB/s] SPACES_ZERO_GPU_DEBUG self.arg_queue._writer.fileno()=11 SPACES_ZERO_GPU_DEBUG self.res_queue._writer.fileno()=13 Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 154, in worker_init torch.move(callback=callback) File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/patching.py", line 450, in move e.submit(copy_context().run, _move, callback=callback).result() File "/usr/local/lib/python3.10/concurrent/futures/_base.py", line 458, in result return self.__get_result() File "/usr/local/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result raise self._exception File "/usr/local/lib/python3.10/concurrent/futures/thread.py", line 58, in run result = self.fn(*self.args, **self.kwargs) File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/patching.py", line 433, in _move original_cuda = original.pin_memory().cuda(non_blocking=True) RuntimeError: NVML_SUCCESS == r INTERNAL ASSERT FAILED at "/pytorch/c10/cuda/CUDACachingAllocator.cpp":1131, please report a bug to PyTorch. Traceback (most recent call last): File "/home/user/app/app.py", line 346, in <module> optimize_pipeline_(pipe, prompt="prompt") File "/home/user/app/optimization.py", line 67, in optimize_pipeline_ compiled = compile_transformer() File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 238, in gradio_handler raise error("ZeroGPU worker error", res.error_cls) gradio.exceptions.Error: 'RuntimeError'

Container logs: