Can't expert_portv2 maybe is operation error

[guoyanzhongwgfufg]

Thank your releases
I run python3 export_v2.py --encoder vitb --input-size 518,error is as follows, already upgrade urllib3 (2.2.2) or chardet (5.2.0),maybe is operation error ,

error is as follows,

kiosk@ubuntu-c:~/worker/deep estimation/tensorrt_version/Depth-Anything-V2$ python3 export_v2.py --encoder vitb --input-size 518

/usr/lib/python3/dist-packages/requests/init.py:89: RequestsDependencyWarning: urllib3 (2.2.2) or chardet (5.2.0) doesn't match a supported version!
warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported "
Traceback (most recent call last):
File "export_v2.py", line 47, in
main()
File "export_v2.py", line 37, in main
example_output = depth_anything.forward(dummy_input)
File "/home/kiosk/worker/deep estimation/tensorrt_version/Depth-Anything-V2/depth_anything_v2/dpt.py", line 179, in forward
features = self.pretrained.get_intermediate_layers(x, self.intermediate_layer_idx[self.encoder], return_class_token=True)
File "/home/kiosk/worker/deep estimation/tensorrt_version/Depth-Anything-V2/depth_anything_v2/dinov2.py", line 308, in get_intermediate_layers
outputs = self._get_intermediate_layers_not_chunked(x, n)
File "/home/kiosk/worker/deep estimation/tensorrt_version/Depth-Anything-V2/depth_anything_v2/dinov2.py", line 277, in _get_intermediate_layers_not_chunked
x = blk(x)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/home/kiosk/worker/deep estimation/tensorrt_version/Depth-Anything-V2/depth_anything_v2/dinov2_layers/block.py", line 247, in forward
return super().forward(x_or_x_list)
File "/home/kiosk/worker/deep estimation/tensorrt_version/Depth-Anything-V2/depth_anything_v2/dinov2_layers/block.py", line 105, in forward
x = x + attn_residual_func(x)
File "/home/kiosk/worker/deep estimation/tensorrt_version/Depth-Anything-V2/depth_anything_v2/dinov2_layers/block.py", line 84, in attn_residual_func
return self.ls1(self.attn(self.norm1(x)))
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/home/kiosk/worker/deep estimation/tensorrt_version/Depth-Anything-V2/depth_anything_v2/dinov2_layers/attention.py", line 76, in forward
x = memory_efficient_attention(q, k, v, attn_bias=attn_bias)
File "/home/kiosk/.local/lib/python3.8/site-packages/xformers/ops/fmha/init.py", line 276, in memory_efficient_attention
return _memory_efficient_attention(
File "/home/kiosk/.local/lib/python3.8/site-packages/xformers/ops/fmha/init.py", line 403, in _memory_efficient_attention
return _fMHA.apply(
File "/usr/local/lib/python3.8/dist-packages/torch/autograd/function.py", line 598, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
File "/home/kiosk/.local/lib/python3.8/site-packages/xformers/ops/fmha/init.py", line 74, in forward
out, op_ctx = _memory_efficient_attention_forward_requires_grad(
File "/home/kiosk/.local/lib/python3.8/site-packages/xformers/ops/fmha/init.py", line 428, in _memory_efficient_attention_forward_requires_grad
op = _dispatch_fw(inp, True)
File "/home/kiosk/.local/lib/python3.8/site-packages/xformers/ops/fmha/dispatch.py", line 119, in _dispatch_fw
return _run_priority_list(
File "/home/kiosk/.local/lib/python3.8/site-packages/xformers/ops/fmha/dispatch.py", line 55, in _run_priority_list
raise NotImplementedError(msg)
NotImplementedError: No operator found for memory_efficient_attention_forward with inputs:
query : shape=(1, 1370, 12, 64) (torch.float32)
key : shape=(1, 1370, 12, 64) (torch.float32)
value : shape=(1, 1370, 12, 64) (torch.float32)
attn_bias : <class 'NoneType'>
p : 0.0
[email protected] is not supported because:
device=cpu (supported: {'cuda'})
dtype=torch.float32 (supported: {torch.bfloat16, torch.float16})
cutlassF is not supported because:
device=cpu (supported: {'cuda'})
smallkF is not supported because:
max(query.shape[-1] != value.shape[-1]) > 32
device=cpu (supported: {'cuda'})
unsupported embed per head: 64

[J4Q8]

Hi! I have exactly the same issue. Have you managed to solve it?