runtime error

Exit code: 1. Reason: <00:03, 1.33GB/s] Downloading (incomplete total...): 96%|█████████▋| 78.3G/81.2G [01:04<00:02, 1.29GB/s] Fetching 32 files: 84%|████████▍ | 27/32 [01:05<00:12, 2.60s/it] Downloading (incomplete total...): 100%|██████████| 81.2G/81.2G [01:06<00:00, 1.48GB/s] Fetching 32 files: 91%|█████████ | 29/32 [01:06<00:05, 1.93s/it] Fetching 32 files: 100%|██████████| 32/32 [01:06<00:00, 2.08s/it] Download complete: 100%|██████████| 81.2G/81.2G [01:06<00:00, 1.48GB/s] Failed to load CPU gemm_4bit_forward from kernels-community: No module named 'kernels'. Please make sure you already `pip install kernels` and the kernels >= 0.11.1 Download complete: 100%|██████████| 81.2G/81.2G [01:07<00:00, 1.20GB/s] Cannot initialize model with low cpu memory usage because `accelerate` was not found in the environment. Defaulting to `low_cpu_mem_usage=False`. It is strongly recommended to install `accelerate` for faster and less memory-intense model loading. You can do so with: ``` pip install accelerate ``` . Traceback (most recent call last): File "/home/user/app/app.py", line 4, in <module> diffusers.WanVACETransformer3DModel.from_pretrained(wanDir, subfolder='transformer', torch_dtype=torch.bfloat16, File "/usr/local/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 88, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/diffusers/models/modeling_utils.py", line 1162, in from_pretrained hf_quantizer.validate_environment(torch_dtype=torch_dtype, from_flax=from_flax, device_map=device_map) File "/usr/local/lib/python3.12/site-packages/diffusers/quantizers/bitsandbytes/bnb_quantizer.py", line 65, in validate_environment raise RuntimeError("No GPU found. A GPU is needed for quantization.") RuntimeError: No GPU found. A GPU is needed for quantization.

Container logs: