runtime error

turn forward_call(*args, **kwargs) File "/home/user/app/ControlNet/ldm/modules/diffusionmodules/model.py", line 258, in forward out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=self.attention_op) File "/home/user/.local/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 192, in memory_efficient_attention return _memory_efficient_attention( File "/home/user/.local/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 290, in _memory_efficient_attention return _memory_efficient_attention_forward( File "/home/user/.local/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 306, in _memory_efficient_attention_forward op = _dispatch_fw(inp) File "/home/user/.local/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 94, in _dispatch_fw return _run_priority_list( File "/home/user/.local/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 69, in _run_priority_list raise NotImplementedError(msg) NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs: query : shape=(1, 6144, 1, 512) (torch.float32) key : shape=(1, 6144, 1, 512) (torch.float32) value : shape=(1, 6144, 1, 512) (torch.float32) attn_bias : <class 'NoneType'> p : 0.0 `cutlassF` is not supported because: device=cpu (supported: {'cuda'}) `flshattF` is not supported because: device=cpu (supported: {'cuda'}) dtype=torch.float32 (supported: {torch.bfloat16, torch.float16}) max(query.shape[-1] != value.shape[-1]) > 128 `tritonflashattF` is not supported because: device=cpu (supported: {'cuda'}) dtype=torch.float32 (supported: {torch.bfloat16, torch.float16}) max(query.shape[-1] != value.shape[-1]) > 128 Operator wasn't built - see `python -m xformers.info` for more info triton is not available `smallkF` is not supported because: max(query.shape[-1] != value.shape[-1]) > 32 unsupported embed per head: 512

Container logs: