Closed yanbing-j closed 1 week ago
Hi @yanbing-j, we also need to add the UT to guard this use case.
since it's a TorchAO UT failure, cc @jerryzh168
cc @msaroufim
This is known and @jerryzh168 is working on a fix. cc @bdhirsh same problem as we saw ealier with inlining triggering tracing of parameterization code.
I re-test on torch 2.5.0.dev20240821+cpu
and torchao 0.4.0+git99644e9
. Some tests in test_int8_weight_only_quant_subclass_api
and test_int4_weight_only_quant_subclass_api
are skipped, and test_int8_weight_only_quant_with_freeze
still fails with a different error.
@anijain2305 @jerryzh168 Any update of this issue?
$ python test/integration/test_integration.py -k test_int8_weight_only_quant_subclass_api
...sss
----------------------------------------------------------------------
Ran 6 tests in 18.891s
OK (skipped=3)
$ python test/integration/test_integration.py -k test_int4_weight_only_quant_subclass_api
ss.sssss.sss
----------------------------------------------------------------------
Ran 12 tests in 12.847s
OK (skipped=10)
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 2239, 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 1251, in compile_fx
return compile_fx(
^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1519, 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 1181, 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 411, 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 147, 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 204, 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 276, in call_function
return target(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_ops.py", line 713, in __call__
return self._op(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yanbingj/project/ao/torchao/dtypes/utils.py", line 57, in _dispatch__torch_function__
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_ops.py", line 713, in __call__
return self._op(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yanbingj/project/ao/torchao/dtypes/utils.py", line 71, 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 39, 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 469, in _fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1238, in __call__
return self._torchdynamo_orig_callable(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1039, in __call__
result = self._inner_convert(
^^^^^^^^^^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 514, in __call__
return _compile(
^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 902, 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 653, 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 686, 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 208, in _fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 622, in transform
tracer.run()
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2780, in run
super().run()
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 979, in run
while self.step():
^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 891, 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 2971, in RETURN_VALUE
self._return(inst)
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2956, 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 39, 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
cc @jerryzh168 Is there an update on the removal of parameterization code?
I thought these are already fixed? the test https://github.com/pytorch/ao/blob/e1039abac7f429a8d7f489d047d9b34d6ac6afe2/test/integration/test_integration.py#L828 is enabled
Hi @jerryzh168,
I verify in torch 2.5.0.dev20240908+cpu and torchao 0.6.0+git3e9746cf (current ao main branch), it still get failures.
(optest) yanbingj@a4bf01945ee1:~/project/ao$ python test/integration/test_integration.py -k test_int8_weight_only_quant_subclass_api
.FFsss
======================================================================
FAIL: test_int8_weight_only_quant_subclass_api_1_cpu (__main__.TestSubclass.test_int8_weight_only_quant_subclass_api_1_cpu)
----------------------------------------------------------------------
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/project/ao/test/integration/test_integration.py", line 821, in test_int8_weight_only_quant_subclass_api
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 804, in _test_lin_weight_subclass_api_impl
self.assertGreater(
AssertionError: tensor(2.3359, dtype=torch.float16) not greater than 40 : _int8wo_api failed when compiled with dtype=torch.float16, (m, k, n)=(32, 64, 32)
======================================================================
FAIL: test_int8_weight_only_quant_subclass_api_2_cpu (__main__.TestSubclass.test_int8_weight_only_quant_subclass_api_2_cpu)
----------------------------------------------------------------------
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/project/ao/test/integration/test_integration.py", line 821, in test_int8_weight_only_quant_subclass_api
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 804, in _test_lin_weight_subclass_api_impl
self.assertGreater(
AssertionError: tensor(2.1562, dtype=torch.bfloat16) not greater than 40 : _int8wo_api failed when compiled with dtype=torch.bfloat16, (m, k, n)=(32, 64, 32)
----------------------------------------------------------------------
Ran 6 tests in 8.907s
FAILED (failures=2, skipped=3)
(optest) yanbingj@a4bf01945ee1:~/project/ao$ python test/integration/test_integration.py -k test_int4_weight_only_quant_subclass_api
ss.sssss.sss
----------------------------------------------------------------------
Ran 12 tests in 8.008s
OK (skipped=10)
(optest) yanbingj@a4bf01945ee1:~/project/ao$ 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 1253, in compile_fx
return compile_fx(
^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1521, 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 1183, 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 413, 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 1253, in compile_fx
return compile_fx(
^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1521, 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 1183, 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 413, 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 1253, in compile_fx
return compile_fx(
^^^^^^^^^^^
File "/home/yanbingj/miniforge3/envs/optest/lib/python3.11/site-packages/torch/_inductor/compile_fx.py", line 1521, 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 1183, 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 413, 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 1.271s
FAILED (errors=3, skipped=3)
(optest) yanbingj@a4bf01945ee1:~/project/ao$
The error of 'PlainAQTLayout' object has no attribute 'layout_type' is fixed.
However, it stll gets failures, will track in https://github.com/pytorch/ao/issues/890 and https://github.com/pytorch/pytorch/issues/135831.
🐛 Describe the bug
torch/ao fails in https://github.com/pytorch/pytorch/commit/f44446e851, which reproducer is
python test/integration/test_integration.py -k test_int8_weight_only_quant_subclass_api
. Even with https://github.com/pytorch/pytorch/tree/gh/anijain2305/467/head, this error still exists.Test Plan: python test/integration/test_integration.py -k test_int8_weight_only_quant_subclass_api python test/integration/test_integration.py -k test_int8_weight_only_quant_with_freeze python test/integration/test_integration.py -k test_int4_weight_only_quant_subclass_api
Versions
$ python collect_env.py Collecting environment information... PyTorch version: 2.5.0a0+git456b0d5 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] flake8==7.1.0 [pip3] numpy==1.26.4 [pip3] optree==0.12.1 [pip3] pytorch-labs-segment-anything-fast==0.2 [pip3] torch==2.5.0a0+git3a355c1 [pip3] torchao==0.3.1+git013cce3 [pip3] torchvision==0.20.0a0+c2619ba [pip3] torchvision==0.20.0a0+c2619ba [pip3] triton-nightly==3.0.0.post20240716052845 [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 dev_0
[conda] torch 2.5.0a0+git3a355c1 dev_0
[conda] torchao 0.3.1+git013cce3 dev_0
[conda] torchvision 0.20.0a0+c2619ba pypi_0 pypi
[conda] triton-nightly 3.0.0.post20240716052845 pypi_0 pypi
cc @ezyang @chauhang @penguinwu