search

pytorch / ao

PyTorch native quantization and sparsity for training and inference
BSD 3-Clause "New" or "Revised" License
755 stars 96 forks source link

[torchao]NotImplementedError: AffineQuantizedTensor dispatch: attempting to run unimplemented operator/function: aten.permute.default #890

Open yanbing-j opened 1 week ago

yanbing-j commented 1 week ago

🐛 Describe the bug

I find there are still errors in torch 2.5.0.dev20240911+cpu and torchao 0.6.0+git3e9746cf.

$ python test/integration/test_integration.py -k test_int8_weight_only_quant_with_freeze
EEEsss
======================================================================
ERROR: test_int8_weight_only_quant_with_freeze_0_cpu (__main__.TestSubclass.test_int8_weight_only_quant_with_freeze_0_cpu)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1446, in _call_user_compiler
    compiled_fn = compiler_fn(gm, self.example_inputs())
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/repro/after_dynamo.py", line 129, in __call__
    compiled_gm = compiler_fn(gm, example_inputs)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/__init__.py", line 2235, in __call__
    return compile_fx(model_, inputs_, config_patches=self.config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1256, in compile_fx
    return compile_fx(
           ^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1524, in compile_fx
    return aot_autograd(
           ^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/backends/common.py", line 72, in __call__
    cg = aot_module_simplified(gm, example_inputs, **self.kwargs)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 1071, in aot_module_simplified
    compiled_fn = dispatch_and_compile()
                  ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 1056, in dispatch_and_compile
    compiled_fn, _ = create_aot_dispatcher_function(
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 522, in create_aot_dispatcher_function
    return _create_aot_dispatcher_function(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 759, in _create_aot_dispatcher_function
    compiled_fn, fw_metadata = compiler_fn(
                               ^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/_aot_autograd/jit_compile_runtime_wrappers.py", line 179, in aot_dispatch_base
    compiled_fw = compiler(fw_module, updated_flat_args)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1186, in fw_compiler_freezing
    opt_model, preserved_arg_indices = freeze(
                                       ^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/freezing.py", line 109, in freeze
    freezing_passes(aot_autograd_gm, aot_example_inputs)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/fx_passes/freezing_patterns.py", line 48, in freezing_passes
    fake_tensor_prop(gm, aot_example_inputs, True)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 414, in fake_tensor_prop
    FakeTensorProp(gm, mode=fake_mode).propagate_dont_convert_inputs(
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/passes/fake_tensor_prop.py", line 70, in propagate_dont_convert_inputs
    return super().run(*args)
           ^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/interpreter.py", line 146, in run
    self.env[node] = self.run_node(node)
                     ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/passes/fake_tensor_prop.py", line 38, in run_node
    result = super().run_node(n)
             ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/interpreter.py", line 203, in run_node
    return getattr(self, n.op)(n.target, args, kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/interpreter.py", line 275, in call_function
    return target(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_ops.py", line 716, in __call__
    return self._op(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/torchao/utils.py", line 375, in _dispatch__torch_function__
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_ops.py", line 716, in __call__
    return self._op(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/torchao/utils.py", line 389, in _dispatch__torch_dispatch__
    raise NotImplementedError(f"{cls.__name__} dispatch: attempting to run unimplemented operator/function: {func}")
NotImplementedError: AffineQuantizedTensor dispatch: attempting to run unimplemented operator/function: aten.permute.default

While executing %permute : [num_users=1] = call_function[target=torch.ops.aten.permute.default](args = (%_frozen_param0, [1, 0]), kwargs = {})
Original traceback:
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/parameterized/parameterized.py", line 620, in standalone_func
    return func(*(a + p.args), **p.kwargs, **kw)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/contextlib.py", line 81, in inner
    return func(*args, **kwds)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/test/integration/test_integration.py", line 829, in test_int8_weight_only_quant_with_freeze
    self._test_lin_weight_subclass_api_impl(
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/test/integration/test_integration.py", line 160, in wrapper
    return test_method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/test/integration/test_integration.py", line 803, in _test_lin_weight_subclass_api_impl
    test_comp = mod_qc(x)
                ^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 465, in _fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1269, in __call__
    return self._torchdynamo_orig_callable(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1064, in __call__
    result = self._inner_convert(
             ^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 526, in __call__
    return _compile(
           ^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 924, in _compile
    guarded_code = compile_inner(code, one_graph, hooks, transform)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 666, in compile_inner
    return _compile_inner(code, one_graph, hooks, transform)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_utils_internal.py", line 87, in wrapper_function
    return function(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 699, in _compile_inner
    out_code = transform_code_object(code, transform)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/bytecode_transformation.py", line 1322, in transform_code_object
    transformations(instructions, code_options)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 219, in _fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 634, in transform
    tracer.run()
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2796, in run
    super().run()
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 983, in run
    while self.step():
          ^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 895, in step
    self.dispatch_table[inst.opcode](self, inst)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2987, in RETURN_VALUE
    self._return(inst)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2972, in _return
    self.output.compile_subgraph(
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1117, in compile_subgraph
    self.compile_and_call_fx_graph(tx, list(reversed(stack_values)), root)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1369, in compile_and_call_fx_graph
    compiled_fn = self.call_user_compiler(gm)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1416, in call_user_compiler
    return self._call_user_compiler(gm)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1465, in _call_user_compiler
    raise BackendCompilerFailed(self.compiler_fn, e) from e
torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised:
NotImplementedError: AffineQuantizedTensor dispatch: attempting to run unimplemented operator/function: aten.permute.default

While executing %permute : [num_users=1] = call_function[target=torch.ops.aten.permute.default](args = (%_frozen_param0, [1, 0]), kwargs = {})
Original traceback:
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)

Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information

You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True

======================================================================
ERROR: test_int8_weight_only_quant_with_freeze_1_cpu (__main__.TestSubclass.test_int8_weight_only_quant_with_freeze_1_cpu)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1446, in _call_user_compiler
    compiled_fn = compiler_fn(gm, self.example_inputs())
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/repro/after_dynamo.py", line 129, in __call__
    compiled_gm = compiler_fn(gm, example_inputs)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/__init__.py", line 2235, in __call__
    return compile_fx(model_, inputs_, config_patches=self.config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1256, in compile_fx
    return compile_fx(
           ^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1524, in compile_fx
    return aot_autograd(
           ^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/backends/common.py", line 72, in __call__
    cg = aot_module_simplified(gm, example_inputs, **self.kwargs)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 1071, in aot_module_simplified
    compiled_fn = dispatch_and_compile()
                  ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 1056, in dispatch_and_compile
    compiled_fn, _ = create_aot_dispatcher_function(
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 522, in create_aot_dispatcher_function
    return _create_aot_dispatcher_function(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 759, in _create_aot_dispatcher_function
    compiled_fn, fw_metadata = compiler_fn(
                               ^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/_aot_autograd/jit_compile_runtime_wrappers.py", line 179, in aot_dispatch_base
    compiled_fw = compiler(fw_module, updated_flat_args)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1186, in fw_compiler_freezing
    opt_model, preserved_arg_indices = freeze(
                                       ^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/freezing.py", line 109, in freeze
    freezing_passes(aot_autograd_gm, aot_example_inputs)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/fx_passes/freezing_patterns.py", line 48, in freezing_passes
    fake_tensor_prop(gm, aot_example_inputs, True)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 414, in fake_tensor_prop
    FakeTensorProp(gm, mode=fake_mode).propagate_dont_convert_inputs(
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/passes/fake_tensor_prop.py", line 70, in propagate_dont_convert_inputs
    return super().run(*args)
           ^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/interpreter.py", line 146, in run
    self.env[node] = self.run_node(node)
                     ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/passes/fake_tensor_prop.py", line 38, in run_node
    result = super().run_node(n)
             ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/interpreter.py", line 203, in run_node
    return getattr(self, n.op)(n.target, args, kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/interpreter.py", line 275, in call_function
    return target(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_ops.py", line 716, in __call__
    return self._op(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/torchao/utils.py", line 375, in _dispatch__torch_function__
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_ops.py", line 716, in __call__
    return self._op(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/torchao/utils.py", line 389, in _dispatch__torch_dispatch__
    raise NotImplementedError(f"{cls.__name__} dispatch: attempting to run unimplemented operator/function: {func}")
NotImplementedError: AffineQuantizedTensor dispatch: attempting to run unimplemented operator/function: aten.permute.default

While executing %permute : [num_users=1] = call_function[target=torch.ops.aten.permute.default](args = (%_frozen_param0, [1, 0]), kwargs = {})
Original traceback:
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/parameterized/parameterized.py", line 620, in standalone_func
    return func(*(a + p.args), **p.kwargs, **kw)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/contextlib.py", line 81, in inner
    return func(*args, **kwds)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/test/integration/test_integration.py", line 829, in test_int8_weight_only_quant_with_freeze
    self._test_lin_weight_subclass_api_impl(
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/test/integration/test_integration.py", line 160, in wrapper
    return test_method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/test/integration/test_integration.py", line 803, in _test_lin_weight_subclass_api_impl
    test_comp = mod_qc(x)
                ^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 465, in _fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1269, in __call__
    return self._torchdynamo_orig_callable(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1064, in __call__
    result = self._inner_convert(
             ^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 526, in __call__
    return _compile(
           ^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 924, in _compile
    guarded_code = compile_inner(code, one_graph, hooks, transform)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 666, in compile_inner
    return _compile_inner(code, one_graph, hooks, transform)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_utils_internal.py", line 87, in wrapper_function
    return function(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 699, in _compile_inner
    out_code = transform_code_object(code, transform)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/bytecode_transformation.py", line 1322, in transform_code_object
    transformations(instructions, code_options)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 219, in _fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 634, in transform
    tracer.run()
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2796, in run
    super().run()
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 983, in run
    while self.step():
          ^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 895, in step
    self.dispatch_table[inst.opcode](self, inst)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2987, in RETURN_VALUE
    self._return(inst)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2972, in _return
    self.output.compile_subgraph(
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1117, in compile_subgraph
    self.compile_and_call_fx_graph(tx, list(reversed(stack_values)), root)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1369, in compile_and_call_fx_graph
    compiled_fn = self.call_user_compiler(gm)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1416, in call_user_compiler
    return self._call_user_compiler(gm)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1465, in _call_user_compiler
    raise BackendCompilerFailed(self.compiler_fn, e) from e
torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised:
NotImplementedError: AffineQuantizedTensor dispatch: attempting to run unimplemented operator/function: aten.permute.default

While executing %permute : [num_users=1] = call_function[target=torch.ops.aten.permute.default](args = (%_frozen_param0, [1, 0]), kwargs = {})
Original traceback:
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)

Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information

You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True

======================================================================
ERROR: test_int8_weight_only_quant_with_freeze_2_cpu (__main__.TestSubclass.test_int8_weight_only_quant_with_freeze_2_cpu)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1446, in _call_user_compiler
    compiled_fn = compiler_fn(gm, self.example_inputs())
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/repro/after_dynamo.py", line 129, in __call__
    compiled_gm = compiler_fn(gm, example_inputs)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/__init__.py", line 2235, in __call__
    return compile_fx(model_, inputs_, config_patches=self.config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1256, in compile_fx
    return compile_fx(
           ^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1524, in compile_fx
    return aot_autograd(
           ^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/backends/common.py", line 72, in __call__
    cg = aot_module_simplified(gm, example_inputs, **self.kwargs)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 1071, in aot_module_simplified
    compiled_fn = dispatch_and_compile()
                  ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 1056, in dispatch_and_compile
    compiled_fn, _ = create_aot_dispatcher_function(
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 522, in create_aot_dispatcher_function
    return _create_aot_dispatcher_function(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/aot_autograd.py", line 759, in _create_aot_dispatcher_function
    compiled_fn, fw_metadata = compiler_fn(
                               ^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_functorch/_aot_autograd/jit_compile_runtime_wrappers.py", line 179, in aot_dispatch_base
    compiled_fw = compiler(fw_module, updated_flat_args)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1186, in fw_compiler_freezing
    opt_model, preserved_arg_indices = freeze(
                                       ^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/freezing.py", line 109, in freeze
    freezing_passes(aot_autograd_gm, aot_example_inputs)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/fx_passes/freezing_patterns.py", line 48, in freezing_passes
    fake_tensor_prop(gm, aot_example_inputs, True)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 414, in fake_tensor_prop
    FakeTensorProp(gm, mode=fake_mode).propagate_dont_convert_inputs(
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/passes/fake_tensor_prop.py", line 70, in propagate_dont_convert_inputs
    return super().run(*args)
           ^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/interpreter.py", line 146, in run
    self.env[node] = self.run_node(node)
                     ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/passes/fake_tensor_prop.py", line 38, in run_node
    result = super().run_node(n)
             ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/interpreter.py", line 203, in run_node
    return getattr(self, n.op)(n.target, args, kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/fx/interpreter.py", line 275, in call_function
    return target(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_ops.py", line 716, in __call__
    return self._op(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/torchao/utils.py", line 375, in _dispatch__torch_function__
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_ops.py", line 716, in __call__
    return self._op(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/torchao/utils.py", line 389, in _dispatch__torch_dispatch__
    raise NotImplementedError(f"{cls.__name__} dispatch: attempting to run unimplemented operator/function: {func}")
NotImplementedError: AffineQuantizedTensor dispatch: attempting to run unimplemented operator/function: aten.permute.default

While executing %permute : [num_users=1] = call_function[target=torch.ops.aten.permute.default](args = (%_frozen_param0, [1, 0]), kwargs = {})
Original traceback:
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/parameterized/parameterized.py", line 620, in standalone_func
    return func(*(a + p.args), **p.kwargs, **kw)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/contextlib.py", line 81, in inner
    return func(*args, **kwds)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/test/integration/test_integration.py", line 829, in test_int8_weight_only_quant_with_freeze
    self._test_lin_weight_subclass_api_impl(
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/test/integration/test_integration.py", line 160, in wrapper
    return test_method(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/project/ao/test/integration/test_integration.py", line 803, in _test_lin_weight_subclass_api_impl
    test_comp = mod_qc(x)
                ^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 465, in _fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1269, in __call__
    return self._torchdynamo_orig_callable(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1064, in __call__
    result = self._inner_convert(
             ^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 526, in __call__
    return _compile(
           ^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 924, in _compile
    guarded_code = compile_inner(code, one_graph, hooks, transform)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 666, in compile_inner
    return _compile_inner(code, one_graph, hooks, transform)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_utils_internal.py", line 87, in wrapper_function
    return function(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 699, in _compile_inner
    out_code = transform_code_object(code, transform)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/bytecode_transformation.py", line 1322, in transform_code_object
    transformations(instructions, code_options)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 219, in _fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 634, in transform
    tracer.run()
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2796, in run
    super().run()
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 983, in run
    while self.step():
          ^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 895, in step
    self.dispatch_table[inst.opcode](self, inst)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2987, in RETURN_VALUE
    self._return(inst)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2972, in _return
    self.output.compile_subgraph(
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1117, in compile_subgraph
    self.compile_and_call_fx_graph(tx, list(reversed(stack_values)), root)
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1369, in compile_and_call_fx_graph
    compiled_fn = self.call_user_compiler(gm)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1416, in call_user_compiler
    return self._call_user_compiler(gm)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1465, in _call_user_compiler
    raise BackendCompilerFailed(self.compiler_fn, e) from e
torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised:
NotImplementedError: AffineQuantizedTensor dispatch: attempting to run unimplemented operator/function: aten.permute.default

While executing %permute : [num_users=1] = call_function[target=torch.ops.aten.permute.default](args = (%_frozen_param0, [1, 0]), kwargs = {})
Original traceback:
  File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)

Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information

You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True

----------------------------------------------------------------------
Ran 6 tests in 1.105s

FAILED (errors=3, skipped=3)

Versions

$ python collect_env.py Collecting environment information... PyTorch version: 2.5.0.dev20240911+cpu Is debug build: False CUDA used to build PyTorch: None ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04 LTS (x86_64) GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 Clang version: 15.0.0 (git@github.com:llvm/llvm-project.git 4ba6a9c9f65bbc8bd06e3652cb20fd4dfc846137) CMake version: version 3.30.0 Libc version: glibc-2.35

Python version: 3.11.9 | packaged by conda-forge | (main, Apr 19 2024, 18:36:13) [GCC 12.3.0] (64-bit runtime) Python platform: Linux-5.16.0-x86_64-with-glibc2.35 Is CUDA available: False CUDA runtime version: No CUDA CUDA_MODULE_LOADING set to: N/A GPU models and configuration: No CUDA Nvidia driver version: No CUDA cuDNN version: No CUDA HIP runtime version: N/A MIOpen runtime version: N/A Is XNNPACK available: True

CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 224 On-line CPU(s) list: 0-223 Vendor ID: GenuineIntel Model name: Intel (R) Xeon (R) CPU Max 9480 CPU family: 6 Model: 143 Thread(s) per core: 2 Core(s) per socket: 56 Socket(s): 2 Stepping: 8 CPU max MHz: 3500.0000 CPU min MHz: 800.0000 BogoMIPS: 3800.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr avx512_fp16 amx_tile flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 5.3 MiB (112 instances) L1i cache: 3.5 MiB (112 instances) L2 cache: 224 MiB (112 instances) L3 cache: 225 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-55,112-167 NUMA node1 CPU(s): 56-111,168-223 Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB filling Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Versions of relevant libraries: [pip3] bert_pytorch==0.0.1a4 [pip3] flake8==7.1.0 [pip3] functorch==1.14.0a0+b71aa0b [pip3] mypy==1.11.2 [pip3] mypy-extensions==1.0.0 [pip3] numpy==1.26.4 [pip3] onnx==1.16.2 [pip3] optree==0.12.1 [pip3] pytorch-labs-segment-anything-fast==0.2 [pip3] torch==2.5.0.dev20240911+cpu [pip3] torch_geometric==2.4.0 [pip3] torchao==0.6.0+git3e9746cf [pip3] torchaudio==2.5.0a0+97ed7b3 [pip3] torchaudio==2.5.0a0+97ed7b3 [pip3] torchmultimodal==0.1.0b0 [pip3] torchvision==0.20.0a0+838ad6c [pip3] torchvision==0.20.0a0+838ad6c [pip3] triton-nightly==3.0.0.post20240716052845 [conda] bert-pytorch 0.0.1a4 dev_0 [conda] functorch 1.14.0a0+b71aa0b pypi_0 pypi [conda] mkl-include 2024.2.0 ha957f24_665 conda-forge [conda] mkl-static 2024.2.0 ha770c72_665 conda-forge [conda] numpy 1.26.4 pypi_0 pypi [conda] optree 0.12.1 pypi_0 pypi [conda] pytorch-labs-segment-anything-fast 0.2 pypi_0 pypi [conda] torch 2.5.0.dev20240911+cpu pypi_0 pypi [conda] torch-geometric 2.4.0 pypi_0 pypi [conda] torchao 0.6.0+git3e9746cf dev_0 [conda] torchaudio 2.5.0a0+97ed7b3 pypi_0 pypi [conda] torchmultimodal 0.1.0b0 pypi_0 pypi [conda] torchvision 0.20.0a0+838ad6c pypi_0 pypi [conda] triton-nightly 3.0.0.post20240716052845 pypi_0 pypi

yanbing-j commented 1 week ago

@msaroufim @bdhirsh @jerryzh168 Could you please take a look? cc @leslie-fang-intel

bdhirsh commented 1 week ago

I can repro with this on a recent torchao commit:

python test/integration/test_integration.py -k test_int8_weight_only_quant_with_freeze_5_cuda

We might be able to make a smaller repro - but it looks like inductor needs some knowledge about which graph inputs are parameters during freezing, and this goes wrong when the parameters are actually subclasses that desugar into a different number of parameters.

cc @IvanKobzarev, do you have bandwidth to take a look? (if not I can grab this one)

leslie-fang-intel commented 1 week ago

Thanks @bdhirsh. Yean, per the discussion with @jerryzh168 in https://github.com/pytorch/ao/pull/884#discussion_r1759431936, I have added the unwrap_tensor_subclass as a workaround in the readme of AO when turning on freezing. Resolving this issue by removing this workaround can definitely improve the user experience.

jerryzh168 commented 1 week ago

sorry just saw this, this should be opened in torchao instead I think

jerryzh168 commented 1 week ago

if we need to implement aten.permute.default we can add that to affine quantized tensor, like: https://github.com/pytorch/ao/blob/d2bce6a56eae5701cb72eb0cf6359626e7bd0190/torchao/dtypes/affine_quantized_tensor.py#L1563. but it seems that @leslie-fang-intel 's workaround can temporary fix this. not sure if we still need to do permute after the tensor subclass is fixed though.

IvanKobzarev commented 2 days ago

136265 is the fix.

The problem:

TracingContext.flat_params contain original params, with not desugared Subclasses. While inductor.freezing API works on aot graphs, which already desugared Subclasses.

flat_params are used only for this logic and storing in them desguared subclasses fixes the issue.

As a result flat_params containing Subclasses in AO test it started calling aten ops like permute on Subclass object and got NYI.

IvanKobzarev commented 7 hours ago

The fix https://github.com/pytorch/pytorch/pull/136265 was merged into master

leslie-fang-intel commented 2 hours ago

Thanks for the fixing. @yanbing-j can you help to verify and close this issue?