Spaces:
Running
on
Zero
why is the space down at the moment
runtime error
Exit code: 1. Reason: k_proj.lora_B.lightx2v_2.weight, blocks.39.attn2.add_k_proj.lora_B.lightx2v_2.bias, blocks.39.attn2.add_v_proj.lora_A.lightx2v_2.weight, blocks.39.attn2.add_v_proj.lora_B.lightx2v_2.weight, blocks.39.attn2.add_v_proj.lora_B.lightx2v_2.bias.
0%| | 0/50 [00:00<?, ?it/s][A
0%| | 0/50 [00:00<?, ?it/s]
skipping cudagraphs due to cpp wrapper enabled
W0913 23:10:40.560000 285 site-packages/torch/_inductor/utils.py:1436] Not enough SMs to use max_autotune_gemm mode
skipping cudagraphs due to cpp wrapper enabled
/usr/local/lib/python3.10/site-packages/gradio/helpers.py:162: UserWarning: In future versions of Gradio, the cache_examples parameter will no longer accept a value of 'lazy'. To enable lazy caching in Gradio, you should set cache_examples=True, and cache_mode='lazy' instead.
warnings.warn(
Will cache examples in '/home/user/app/.gradio/cached_examples/20' directory at first use.
ZeroGPU tensors packing: 0%| | 0.00/35.6G [00:00<?, ?B/s][A
ZeroGPU tensors packing: 0%| | 0.00/35.6G [00:01<?, ?B/s]
Traceback (most recent call last):
File "/home/user/app/app.py", line 261, in
demo.queue().launch(mcp_server=True)
File "/usr/local/lib/python3.10/site-packages/spaces/zero/gradio.py", line 162, in launch
task(*task_args, **task_kwargs)
File "/usr/local/lib/python3.10/site-packages/spaces/zero/init.py", line 24, in startup
total_size = torch.pack()
File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/patching.py", line 397, in pack
total_size = _pack(Config.zerogpu_offload_dir)
File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/patching.py", line 387, in _pack
pack = pack_tensors(originals, fakes, offload_dir, callback=update)
File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/packing.py", line 110, in pack_tensors
fd = os.open(pack.path(), os.O_CREAT | os.O_WRONLY | os.O_DIRECT)
FileNotFoundError: [Errno 2] No such file or directory: '/data-nvme/zerogpu-offload/140538201479904'
Container logs:
Failed to retrieve error logs: SSE is not enabled
anyone facing this issue pls update gradio and replace the torch download with
os.system('pip install --upgrade --pre --extra-index-url https://download.pytorch.org/whl/nightly/cu126 "torch<2.9"')