Is DeepCache by comfyui only supports sizes that are multiples of 32?

[onefish51]

Describe the bug

When I was testing the acceleration inference of DeepCache, I encountered an error when I modified the inference size to 720*960. However, when I modified the inference size to a multiple of 8, there was no error.

This situation is similar to what I previously mentioned #527 (comment) when testing the acceleration of diffusers.

Your environment

OS

Ubuntu 20.04.6 LTS

OneDiff git commit id

Building wheels for collected packages: onediff
  Building editable for onediff (pyproject.toml) ... done
  Created wheel for onediff: filename=onediff-0.13.0.dev1-0.editable-py3-none-any.whl size=5362 sha256=9e86fa1dc8cfefa40c1c163833bc6bf7e9c689012ae7b44dfab6e26ff4423d0f
  Stored in directory: /tmp/pip-ephem-wheel-cache-wqfwl901/wheels/b4/62/0d/0a502b53cf9cb2a2f46a88e2251c723c39df227d4f44413c4d
Successfully built onediff
Installing collected packages: onediff
  Attempting uninstall: onediff
    Found existing installation: onediff 0.13.0.dev1
    Uninstalling onediff-0.13.0.dev1:
      Successfully uninstalled onediff-0.13.0.dev1
Successfully installed onediff-0.13.0.dev1

OneFlow version info

libibverbs not available, ibv_fork_init skipped
Ignoring PCI device with non-16bit domain.
Pass --enable-32bits-pci-domain to configure to support such devices
(warning: it would break the library ABI, don't enable unless really needed).
path: ['/opt/conda/lib/python3.10/site-packages/oneflow']
version: 0.9.1.dev20240219+cu121
git_commit: 6621521
cmake_build_type: Release
rdma: True
mlir: True
enterprise: False

How To Reproduce

workflow_deepcache.json

The complete error message

Prompt executed in 1.54 seconds
got prompt
[ERROR](GRAPH:OneflowGraph_0:OneflowGraph) run got error: <class 'oneflow._oneflow_internal.exception.Exception'> Check failed: (45 == 46) 
  File "oneflow/core/job/job_interpreter.cpp", line 307, in InterpretJob
    RunNormalOp(launch_context, launch_op, inputs)
  File "oneflow/core/job/job_interpreter.cpp", line 219, in RunNormalOp
    it.Apply(*op, inputs, &outputs, OpExprInterpContext(empty_attr_map, JUST(launch_op.device)))
  File "oneflow/core/framework/op_interpreter/eager_local_op_interpreter.cpp", line 84, in NaiveInterpret
    [&]() -> Maybe<const LocalTensorInferResult> { LocalTensorMetaInferArgs ... mut_local_tensor_infer_cache()->GetOrInfer(infer_args)); }()
  File "oneflow/core/framework/op_interpreter/eager_local_op_interpreter.cpp", line 87, in operator()
    user_op_expr.mut_local_tensor_infer_cache()->GetOrInfer(infer_args)
  File "oneflow/core/framework/local_tensor_infer_cache.cpp", line 210, in GetOrInfer
    Infer(*user_op_expr, infer_args)
  File "oneflow/core/framework/local_tensor_infer_cache.cpp", line 178, in Infer
    user_op_expr.InferPhysicalTensorDesc( infer_args.attrs ... ) -> TensorMeta* { return &output_mut_metas.at(i); })
  File "oneflow/core/framework/op_expr.cpp", line 602, in InferPhysicalTensorDesc
    physical_tensor_desc_infer_fn_(&infer_ctx)
  File "oneflow/user/ops/concat_op.cpp", line 55, in InferLogicalTensorDesc
    CHECK_EQ_OR_RETURN(in_desc.shape().At(i), out_dim_vec.at(i))
Error Type: oneflow.ErrorProto.check_failed_error
Exception in __call__: e=Exception('Check failed: (45 == 46) \n  File "oneflow/core/job/job_interpreter.cpp", line 307, in InterpretJob\n    RunNormalOp(launch_context, launch_op, inputs)\n  File "oneflow/core/job/job_interpreter.cpp", line 219, in RunNormalOp\n    it.Apply(*op, inputs, &outputs, OpExprInterpContext(empty_attr_map, JUST(launch_op.device)))\n  File "oneflow/core/framework/op_interpreter/eager_local_op_interpreter.cpp", line 84, in NaiveInterpret\n    [&]() -> Maybe<const LocalTensorInferResult> { LocalTensorMetaInferArgs ... mut_local_tensor_infer_cache()->GetOrInfer(infer_args)); }()\n  File "oneflow/core/framework/op_interpreter/eager_local_op_interpreter.cpp", line 87, in operator()\n    user_op_expr.mut_local_tensor_infer_cache()->GetOrInfer(infer_args)\n  File "oneflow/core/framework/local_tensor_infer_cache.cpp", line 210, in GetOrInfer\n    Infer(*user_op_expr, infer_args)\n  File "oneflow/core/framework/local_tensor_infer_cache.cpp", line 178, in Infer\n    user_op_expr.InferPhysicalTensorDesc( infer_args.attrs ... ) -> TensorMeta* { return &output_mut_metas.at(i); })\n  File "oneflow/core/framework/op_expr.cpp", line 602, in InferPhysicalTensorDesc\n    physical_tensor_desc_infer_fn_(&infer_ctx)\n  File "oneflow/user/ops/concat_op.cpp", line 55, in InferLogicalTensorDesc\n    CHECK_EQ_OR_RETURN(in_desc.shape().At(i), out_dim_vec.at(i))\nError Type: oneflow.ErrorProto.check_failed_error')
Recompile oneflow module ...
Building a graph for <class 'register_comfy.deep_cache_unet.DeepCacheUNet'> ...
Prompt executed in 41.97 seconds

[strint]

We have fixed this, please update and have a try.

[strint]

too old to follow, please feel free to reopen it.