runtime error
Exit code: 1. Reason: οΏ½βββββββββ| 254M/254M [00:01<00:00, 203MB/s] Loading pipeline components...: 0%| | 0/5 [00:00<?, ?it/s][A Loading checkpoint shards: 0%| | 0/9 [00:00<?, ?it/s][A Loading checkpoint shards: 33%|ββββ | 3/9 [00:01<00:02, 2.64it/s][A Loading checkpoint shards: 67%|βββββββ | 6/9 [00:02<00:01, 2.79it/s][A Loading checkpoint shards: 100%|ββββββββββ| 9/9 [00:03<00:00, 2.94it/s] Loading pipeline components...: 40%|ββββ | 2/5 [00:04<00:06, 2.08s/it][A`torch_dtype` is deprecated! Use `dtype` instead! Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s][A Loading checkpoint shards: 100%|ββββββββββ| 4/4 [00:00<00:00, 5.07it/s] Loading pipeline components...: 80%|ββββββββ | 4/5 [00:06<00:01, 1.41s/it][A Loading pipeline components...: 100%|ββββββββββ| 5/5 [00:06<00:00, 1.21s/it] Qwen-Image-2512-Lightning-4steps-V1.0-bf(β¦): 0%| | 0.00/850M [00:00<?, ?B/s][A Qwen-Image-2512-Lightning-4steps-V1.0-bf(β¦): 8%|β | 68.6M/850M [00:01<00:15, 49.8MB/s][A Qwen-Image-2512-Lightning-4steps-V1.0-bf(β¦): 100%|ββββββββββ| 850M/850M [00:02<00:00, 365MB/s] Waiting for a GPU to become available Traceback (most recent call last): File "/home/user/app/app.py", line 140, 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 186, in gradio_handler schedule_response = client.schedule(task_id=task_id, request=request, duration=duration_) File "/usr/local/lib/python3.10/site-packages/spaces/zero/client.py", line 202, in schedule raise error("ZeroGPU quota exceeded", message) gradio.exceptions.Error: 'No GPU was available after 60s. Try re-running outside of examples if it happened after clicking one'
Container logs:
Fetching error logs...