Errors while trying to create a .pte file for gemma 3 #16411
Description
🐛 Describe the bug
I ran:
conda create -n optimum-executorch python=3.11
conda activate optimum-executorch
git clone https://github.com/huggingface/optimum-executorch.git
cd optimum-executorch
pip install '.[dev]'
Ran:
optimum-cli export executorch \
--model "google/gemma-3-4b-it" \
--task "multimodal-text-to-text" \
--recipe "cuda" \
--dtype bfloat16 \
--device cuda \
--qlinear 4w \
--qlinear_encoder 4w \
--qlinear_packing_format tile_packed_to_4d \
--qlinear_encoder_packing_format tile_packed_to_4d \
--output_dir="/scratch/hmaurya/executorch/gemma"
I am getting:
Skipping import of cpp extensions due to incompatible torch version 2.9.1+cu128 for torchao version 0.14.0 Please see GitHub issue #2919 for more info
Loading weights: 100%|█| 883/883 [00:39<00:00, 22.49it/s, Materializing param=model.vision_
Traceback (most recent call last):
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/bin/optimum-cli", line 7, in <module>
sys.exit(main())
^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/commands/optimum_cli.py", line 219, in main
service.run()
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/commands/export/executorch.py", line 267, in run
main_export(
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/__main__.py", line 138, in main_export
model = task_func(model_name_or_path, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/tasks/multimodal_text_to_text.py", line 167, in load_multimodal_text_to_text_model
quantize_model_(**quantize_decoder_kwargs)
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/quantization.py", line 34, in quantize_model_
from torchao.experimental.quant_api import UIntxWeightOnlyConfig
ImportError: cannot import name 'UIntxWeightOnlyConfig' from 'torchao.experimental.quant_api' (/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torchao/experimental/quant_api.py)
as I am not using quant_config_key == "fpa4w" so I commented out its import and its usage.... but then I get:
Skipping import of cpp extensions due to incompatible torch version 2.9.1+cu128 for torchao version 0.14.0 Please see GitHub issue #2919 for more info
Loading weights: 100%|█| 883/883 [00:04<00:00, 186.10it/s, Materializing param=model.vision
`torch_dtype` is deprecated! Use `dtype` instead!
WARNING:coremltools:scikit-learn version 1.7.1 is not supported. Minimum required version: 0.17. Maximum required version: 1.5.1. Disabling scikit-learn conversion API.
WARNING:coremltools:Torch version 2.9.1+cu128 has not been tested with coremltools. You may run into unexpected errors. Torch 2.7.0 is the most recent version that has been tested.
WARNING:coremltools:Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLCPUComputeDeviceProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLGPUComputeDeviceProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLNeuralEngineComputeDeviceProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLComputePlanProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLModelAssetProxy: No module named 'coremltools.libcoremlpython'
I tokenizers:regex.cpp:27] Registering override fallback regex
/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/output_graph.py:1711: UserWarning: While exporting, we found certain side effects happened in the model.forward. Here are the list of potential sources you can double check: ["L['self'].cache.layers[0]", "L['self'].cache.layers[1]", "L['self'].cache.layers[2]", "L['self'].cache.layers[3]", "L['self'].cache.layers[4]", "L['self'].cache.layers[6]", "L['self'].cache.layers[7]", "L['self'].cache.layers[8]", "L['self'].cache.layers[9]", "L['self'].cache.layers[10]", "L['self'].cache.layers[12]", "L['self'].cache.layers[13]", "L['self'].cache.layers[14]", "L['self'].cache.layers[15]", "L['self'].cache.layers[16]", "L['self'].cache.layers[18]", "L['self'].cache.layers[19]", "L['self'].cache.layers[20]", "L['self'].cache.layers[21]", "L['self'].cache.layers[22]", "L['self'].cache.layers[24]", "L['self'].cache.layers[25]", "L['self'].cache.layers[26]", "L['self'].cache.layers[27]", "L['self'].cache.layers[28]", "L['self'].cache.layers[30]", "L['self'].cache.layers[31]", "L['self'].cache.layers[32]", "L['self'].cache.layers[33]"]
warnings.warn(
Traceback (most recent call last):
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/bin/optimum-cli", line 7, in <module>
sys.exit(main())
^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/commands/optimum_cli.py", line 219, in main
service.run()
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/commands/export/executorch.py", line 267, in run
main_export(
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/__main__.py", line 145, in main_export
return export_to_executorch(
^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/convert.py", line 79, in export_to_executorch
executorch_progs = recipe_func(model, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/recipes/cuda.py", line 148, in export_to_executorch_with_cuda
exported_progs = model.export()
^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/integrations.py", line 339, in export
exported_program = torch.export.export(
^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/__init__.py", line 311, in export
raise e
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/__init__.py", line 277, in export
return _export(
^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 1163, in wrapper
raise e
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 1129, in wrapper
ep = fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/exported_program.py", line 124, in wrapper
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 2255, in _export
ep = _export_for_training(
^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 1163, in wrapper
raise e
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 1129, in wrapper
ep = fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/exported_program.py", line 124, in wrapper
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 2071, in _export_for_training
export_artifact = export_func(
^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 1415, in _strict_export
gm_torch_level = _export_to_torch_ir(
^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 812, in _export_to_torch_ir
gm_torch_level, _ = torch._dynamo.export(
^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 2002, in inner
result_traced = opt_f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 414, in __call__
return super().__call__(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 832, in compile_wrapper
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/fx/graph_module.py", line 837, in call_wrapped
return self._wrapped_call(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/fx/graph_module.py", line 413, in __call__
raise e
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/fx/graph_module.py", line 400, in __call__
return super(self.cls, obj).__call__(*args, **kwargs) # type: ignore[misc]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1878, in _call_impl
return inner()
^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1829, in inner
result = forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1875, in __call__
result = self._torchdynamo_orig_backend(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 688, in __call__
result = _compile(
^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1495, in _compile
raise InternalTorchDynamoError(
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1434, in _compile
guarded_code, tracer_output = compile_inner(code, one_graph, hooks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_utils_internal.py", line 92, in wrapper_function
return function(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1117, in compile_inner
return _compile_inner(code, one_graph, hooks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1151, in _compile_inner
dynamo_output = compile_frame(
^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1032, in compile_frame
bytecode, tracer_output = transform_code_object(code, transform)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/bytecode_transformation.py", line 1592, in transform_code_object
tracer_output = transformations(instructions, code_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1004, in transform
tracer_output = trace_frame(
^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 312, in _fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 815, in trace_frame
run_tracer()
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 797, in run_tracer
tracer.run()
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 1500, in run
while self.step():
^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 1348, in step
self.dispatch_table[inst.opcode](self, inst)
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2450, in LOAD_ATTR
self._load_attr(inst)
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2438, in _load_attr
result = BuiltinVariable(getattr).call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 1347, in call_function
return handler(tx, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 966, in <lambda>
return lambda tx, args, kwargs: obj.call_function(
^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 1347, in call_function
return handler(tx, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 1154, in builtin_dispatch
rv = fn(tx, args, kwargs)
^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 1032, in call_self_handler
result = self_handler(tx, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 2290, in call_getattr
return obj.var_getattr(tx, name)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/nn_module.py", line 377, in var_getattr
if isinstance(out, (NNModuleVariable, UnspecializedNNModuleVariable)):
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/base.py", line 227, in __instancecheck__
instance = instance.realize()
^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/lazy.py", line 72, in realize
self._cache.realize()
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/lazy.py", line 33, in realize
self.vt = builder.VariableBuilder(tx, self.source)(self.value)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 446, in __call__
vt = self._wrap(value)
^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 697, in _wrap
return self.wrap_tensor(value)
^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2019, in wrap_tensor
return self.tx.output.register_attr_or_module(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1127, in register_attr_or_module
return wrap_name(name)
^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1037, in wrap_name
vt = wrap_fx_proxy(
^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2645, in wrap_fx_proxy
return wrap_fx_proxy_cls(target_cls=TensorVariable, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2715, in wrap_fx_proxy_cls
return _wrap_fx_preexisting_tensor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2758, in _wrap_fx_preexisting_tensor
cache_real_value_when_export(tx, proxy, tensor)
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2658, in cache_real_value_when_export
proxy.tracer.real_value_cache[proxy.node] = _clone_input(
^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2629, in _clone_input
value = clone_input(value)
^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/utils.py", line 2155, in clone_input
result.copy_(x.clone())
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torchao/utils.py", line 674, in _dispatch__torch_dispatch__
return cls._ATEN_OP_OR_TORCH_FN_TABLE[cls][func](func, types, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torchao/utils.py", line 491, in wrapper
return func(f, types, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torchao/utils.py", line 567, in _
if _same_metadata(self, src):
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torchao/utils.py", line 530, in _same_metadata
for t_name in self.tensor_data_names
^^^^^^^^^^^^^^^^^^^^^^
torch._dynamo.exc.InternalTorchDynamoError: AttributeError: 'Tensor' object has no attribute 'tensor_data_names'
from user code:
File "<eval_with_key>.23", line 687, in forward
model_lm_head_weight = self.model.lm_head.weight
Set TORCHDYNAMO_VERBOSE=1 for the internal stack trace (please do this especially if you're reporting a bug to PyTorch). For even more developer context, set TORCH_LOGS="+dynamo"
and when I tried:
optimum-cli export executorch --model "google/gemma-3-4b-it" --task "multimodal-text-to-text" --recipe "cuda" --dtype bfloat16 --device cuda --output_dir="/scratch/hmaurya/executorch/gemma"
error:
Skipping import of cpp extensions due to incompatible torch version 2.9.1+cu128 for torchao version 0.14.0 Please see GitHub issue #2919 for more info
Loading weights: 100%|█| 883/883 [00:03<00:00, 233.86it/s, Materializing param=model.vision
`torch_dtype` is deprecated! Use `dtype` instead!
WARNING:coremltools:scikit-learn version 1.7.1 is not supported. Minimum required version: 0.17. Maximum required version: 1.5.1. Disabling scikit-learn conversion API.
WARNING:coremltools:Torch version 2.9.1+cu128 has not been tested with coremltools. You may run into unexpected errors. Torch 2.7.0 is the most recent version that has been tested.
WARNING:coremltools:Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLCPUComputeDeviceProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLGPUComputeDeviceProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLNeuralEngineComputeDeviceProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLComputePlanProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLModelAssetProxy: No module named 'coremltools.libcoremlpython'
I tokenizers:regex.cpp:27] Registering override fallback regex
/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/output_graph.py:1711: UserWarning: While exporting, we found certain side effects happened in the model.forward. Here are the list of potential sources you can double check: ["L['self'].cache.layers[0]", "L['self'].cache.layers[1]", "L['self'].cache.layers[2]", "L['self'].cache.layers[3]", "L['self'].cache.layers[4]", "L['self'].cache.layers[6]", "L['self'].cache.layers[7]", "L['self'].cache.layers[8]", "L['self'].cache.layers[9]", "L['self'].cache.layers[10]", "L['self'].cache.layers[12]", "L['self'].cache.layers[13]", "L['self'].cache.layers[14]", "L['self'].cache.layers[15]", "L['self'].cache.layers[16]", "L['self'].cache.layers[18]", "L['self'].cache.layers[19]", "L['self'].cache.layers[20]", "L['self'].cache.layers[21]", "L['self'].cache.layers[22]", "L['self'].cache.layers[24]", "L['self'].cache.layers[25]", "L['self'].cache.layers[26]", "L['self'].cache.layers[27]", "L['self'].cache.layers[28]", "L['self'].cache.layers[30]", "L['self'].cache.layers[31]", "L['self'].cache.layers[32]", "L['self'].cache.layers[33]"]
warnings.warn(
W1230 00:51:22.887000 596761 site-packages/torch/fx/experimental/symbolic_shapes.py:6833] [1/0] _maybe_guard_rel() was called on non-relation expression Eq(s29, s58) | Eq(s58, 1)
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
tokenizer_config.json: 100%|██████████████████████████| 1.16M/1.16M [00:00<00:00, 23.1MB/s]
tokenizer.json: 100%|█████████████████████████████████| 33.4M/33.4M [00:00<00:00, 76.4MB/s]
added_tokens.json: 100%|█████████████████████████████████| 35.0/35.0 [00:00<00:00, 173kB/s]
special_tokens_map.json: 100%|████████████████████████████| 662/662 [00:00<00:00, 3.67MB/s]
Traceback (most recent call last):
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/bin/optimum-cli", line 7, in <module>
sys.exit(main())
^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/commands/optimum_cli.py", line 219, in main
service.run()
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/commands/export/executorch.py", line 267, in run
main_export(
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/__main__.py", line 145, in main_export
return export_to_executorch(
^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/convert.py", line 79, in export_to_executorch
executorch_progs = recipe_func(model, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/recipes/cuda.py", line 150, in export_to_executorch_with_cuda
return lower_to_executorch(exported_progs, model.metadata, model_config=getattr(model, "config", None))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/recipes/cuda.py", line 54, in lower_to_executorch
from torch._inductor.decomposition import conv1d_to_conv2d
ImportError: cannot import name 'conv1d_to_conv2d' from 'torch._inductor.decomposition' (/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_inductor/decomposition.py)
then I tried: pytorch/ao#2919 (comment) but still got the same error:
(optimum-executorch) [hmaurya@hyper-01-prod-comp-di-0242-66 optimum-executorch]$ optimum-cli export executorch --model "google/gemma-3-4b-it" --task "multimodal-text-to-text" --recipe "cuda" --dtype bfloat16 --device cuda --qlinear 4w --qlinear_encoder 4w --qlinear_packing_format tile_packed_to_4d --qlinear_encoder_packing_format tile_packed_to_4d --output_dir="/scratch/hmaurya/executorch/gemma"
Skipping import of cpp extensions due to incompatible torch version 2.9.1+cu128 for torchao version 0.14.1+cu129 Please see https://github.com/pytorch/ao/issues/2919 for more info
TMA benchmarks will be running without grid constant TMA descriptor.
Loading weights: 100%|█| 883/883 [00:41<00:00, 21.05it/s, Materializing param=model.vision_
`torch_dtype` is deprecated! Use `dtype` instead!
WARNING:coremltools:scikit-learn version 1.7.1 is not supported. Minimum required version: 0.17. Maximum required version: 1.5.1. Disabling scikit-learn conversion API.
WARNING:coremltools:Torch version 2.9.1+cu128 has not been tested with coremltools. You may run into unexpected errors. Torch 2.7.0 is the most recent version that has been tested.
WARNING:coremltools:Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLCPUComputeDeviceProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLGPUComputeDeviceProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLNeuralEngineComputeDeviceProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLComputePlanProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython'
WARNING:coremltools:Failed to load _MLModelAssetProxy: No module named 'coremltools.libcoremlpython'
I tokenizers:regex.cpp:27] Registering override fallback regex
/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/output_graph.py:1711: UserWarning: While exporting, we found certain side effects happened in the model.forward. Here are the list of potential sources you can double check: ["L['self'].cache.layers[0]", "L['self'].cache.layers[1]", "L['self'].cache.layers[2]", "L['self'].cache.layers[3]", "L['self'].cache.layers[4]", "L['self'].cache.layers[6]", "L['self'].cache.layers[7]", "L['self'].cache.layers[8]", "L['self'].cache.layers[9]", "L['self'].cache.layers[10]", "L['self'].cache.layers[12]", "L['self'].cache.layers[13]", "L['self'].cache.layers[14]", "L['self'].cache.layers[15]", "L['self'].cache.layers[16]", "L['self'].cache.layers[18]", "L['self'].cache.layers[19]", "L['self'].cache.layers[20]", "L['self'].cache.layers[21]", "L['self'].cache.layers[22]", "L['self'].cache.layers[24]", "L['self'].cache.layers[25]", "L['self'].cache.layers[26]", "L['self'].cache.layers[27]", "L['self'].cache.layers[28]", "L['self'].cache.layers[30]", "L['self'].cache.layers[31]", "L['self'].cache.layers[32]", "L['self'].cache.layers[33]"]
warnings.warn(
Traceback (most recent call last):
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/bin/optimum-cli", line 7, in <module>
sys.exit(main())
^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/commands/optimum_cli.py", line 219, in main
service.run()
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/commands/export/executorch.py", line 267, in run
main_export(
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/__main__.py", line 145, in main_export
return export_to_executorch(
^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/convert.py", line 79, in export_to_executorch
executorch_progs = recipe_func(model, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/recipes/cuda.py", line 148, in export_to_executorch_with_cuda
exported_progs = model.export()
^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/optimum/exporters/executorch/integrations.py", line 339, in export
exported_program = torch.export.export(
^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/__init__.py", line 311, in export
raise e
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/__init__.py", line 277, in export
return _export(
^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 1163, in wrapper
raise e
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 1129, in wrapper
ep = fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/exported_program.py", line 124, in wrapper
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 2255, in _export
ep = _export_for_training(
^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 1163, in wrapper
raise e
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 1129, in wrapper
ep = fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/exported_program.py", line 124, in wrapper
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 2071, in _export_for_training
export_artifact = export_func(
^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 1415, in _strict_export
gm_torch_level = _export_to_torch_ir(
^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/export/_trace.py", line 812, in _export_to_torch_ir
gm_torch_level, _ = torch._dynamo.export(
^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 2002, in inner
result_traced = opt_f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 414, in __call__
return super().__call__(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 832, in compile_wrapper
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/fx/graph_module.py", line 837, in call_wrapped
return self._wrapped_call(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/fx/graph_module.py", line 413, in __call__
raise e
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/fx/graph_module.py", line 400, in __call__
return super(self.cls, obj).__call__(*args, **kwargs) # type: ignore[misc]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1878, in _call_impl
return inner()
^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1829, in inner
result = forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1875, in __call__
result = self._torchdynamo_orig_backend(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 688, in __call__
result = _compile(
^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1495, in _compile
raise InternalTorchDynamoError(
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1434, in _compile
guarded_code, tracer_output = compile_inner(code, one_graph, hooks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_utils_internal.py", line 92, in wrapper_function
return function(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1117, in compile_inner
return _compile_inner(code, one_graph, hooks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1151, in _compile_inner
dynamo_output = compile_frame(
^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1032, in compile_frame
bytecode, tracer_output = transform_code_object(code, transform)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/bytecode_transformation.py", line 1592, in transform_code_object
tracer_output = transformations(instructions, code_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 1004, in transform
tracer_output = trace_frame(
^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 312, in _fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 815, in trace_frame
run_tracer()
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 797, in run_tracer
tracer.run()
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 1500, in run
while self.step():
^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 1348, in step
self.dispatch_table[inst.opcode](self, inst)
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2450, in LOAD_ATTR
self._load_attr(inst)
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/symbolic_convert.py", line 2438, in _load_attr
result = BuiltinVariable(getattr).call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 1347, in call_function
return handler(tx, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 966, in <lambda>
return lambda tx, args, kwargs: obj.call_function(
^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 1347, in call_function
return handler(tx, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 1154, in builtin_dispatch
rv = fn(tx, args, kwargs)
^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 1032, in call_self_handler
result = self_handler(tx, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builtin.py", line 2290, in call_getattr
return obj.var_getattr(tx, name)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/nn_module.py", line 377, in var_getattr
if isinstance(out, (NNModuleVariable, UnspecializedNNModuleVariable)):
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/base.py", line 227, in __instancecheck__
instance = instance.realize()
^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/lazy.py", line 72, in realize
self._cache.realize()
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/lazy.py", line 33, in realize
self.vt = builder.VariableBuilder(tx, self.source)(self.value)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 446, in __call__
vt = self._wrap(value)
^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 697, in _wrap
return self.wrap_tensor(value)
^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2019, in wrap_tensor
return self.tx.output.register_attr_or_module(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1127, in register_attr_or_module
return wrap_name(name)
^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/output_graph.py", line 1037, in wrap_name
vt = wrap_fx_proxy(
^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2645, in wrap_fx_proxy
return wrap_fx_proxy_cls(target_cls=TensorVariable, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2715, in wrap_fx_proxy_cls
return _wrap_fx_preexisting_tensor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2758, in _wrap_fx_preexisting_tensor
cache_real_value_when_export(tx, proxy, tensor)
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2658, in cache_real_value_when_export
proxy.tracer.real_value_cache[proxy.node] = _clone_input(
^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/variables/builder.py", line 2629, in _clone_input
value = clone_input(value)
^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torch/_dynamo/utils.py", line 2155, in clone_input
result.copy_(x.clone())
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torchao/utils.py", line 674, in _dispatch__torch_dispatch__
return cls._ATEN_OP_OR_TORCH_FN_TABLE[cls][func](func, types, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torchao/utils.py", line 491, in wrapper
return func(f, types, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torchao/utils.py", line 567, in _
if _same_metadata(self, src):
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/group/anantm-g00/hmaurya/envs/optimum-executorch/lib/python3.11/site-packages/torchao/utils.py", line 530, in _same_metadata
for t_name in self.tensor_data_names
^^^^^^^^^^^^^^^^^^^^^^
torch._dynamo.exc.InternalTorchDynamoError: AttributeError: 'Tensor' object has no attribute 'tensor_data_names'
from user code:
File "<eval_with_key>.23", line 687, in forward
model_lm_head_weight = self.model.lm_head.weight
Set TORCHDYNAMO_VERBOSE=1 for the internal stack trace (please do this especially if you're reporting a bug to PyTorch). For even more developer context, set TORCH_LOGS="+dynamo"
Versions
(optimum-executorch) [hmaurya@hyper-01-prod-comp-di-0242-66 optimum-executorch]$ python collect_env.py
Collecting environment information...
PyTorch version: 2.9.1+cu128
Is debug build: False
CUDA used to build PyTorch: 12.8
ROCM used to build PyTorch: N/A
OS: Amazon Linux 2023.5.20240701 (x86_64)
GCC version: (GCC) 11.4.1 20230605 (Red Hat 11.4.1-2)
Clang version: Could not collect
CMake version: version 3.22.2
Libc version: glibc-2.34
Python version: 3.11.14 (main, Oct 21 2025, 18:31:21) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.1.94-99.176.amzn2023.x86_64-x86_64-with-glibc2.34
Is CUDA available: True
CUDA runtime version: 12.2.140
CUDA_MODULE_LOADING set to:
GPU models and configuration:
GPU 0: NVIDIA H200
GPU 1: NVIDIA H200
GPU 2: NVIDIA H200
GPU 3: NVIDIA H200
GPU 4: NVIDIA H200
GPU 5: NVIDIA H200
GPU 6: NVIDIA H200
GPU 7: NVIDIA H200
Nvidia driver version: 570.133.20
cuDNN version: Could not collect
Is XPU available: False
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
Caching allocator config: N/A
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 192
On-line CPU(s) list: 0-191
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8488C
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 48
Socket(s): 2
Stepping: 8
BogoMIPS: 4800.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd ida arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid cldemote movdiri movdir64b md_clear serialize amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 4.5 MiB (96 instances)
L1i cache: 3 MiB (96 instances)
L2 cache: 192 MiB (96 instances)
L3 cache: 210 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-47,96-143
NUMA node1 CPU(s): 48-95,144-191
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: 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 / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] executorch==1.0.1
[pip3] mypy_extensions==1.1.0
[pip3] numpy==2.3.5
[pip3] nvidia-cublas-cu12==12.8.4.1
[pip3] nvidia-cuda-cupti-cu12==12.8.90
[pip3] nvidia-cuda-nvrtc-cu12==12.8.93
[pip3] nvidia-cuda-runtime-cu12==12.8.90
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cufft-cu12==11.3.3.83
[pip3] nvidia-curand-cu12==10.3.9.90
[pip3] nvidia-cusolver-cu12==11.7.3.90
[pip3] nvidia-cusparse-cu12==12.5.8.93
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] optimum-executorch==0.2.0.dev0
[pip3] pytorch_tokenizers==1.0.1
[pip3] torch==2.9.1
[pip3] torchao==0.14.1+cu129
[pip3] triton==3.5.1
[conda] executorch 1.0.1 pypi_0 pypi
[conda] numpy 2.3.5 pypi_0 pypi
[conda] nvidia-cublas-cu12 12.8.4.1 pypi_0 pypi
[conda] nvidia-cuda-cupti-cu12 12.8.90 pypi_0 pypi
[conda] nvidia-cuda-nvrtc-cu12 12.8.93 pypi_0 pypi
[conda] nvidia-cuda-runtime-cu12 12.8.90 pypi_0 pypi
[conda] nvidia-cudnn-cu12 9.10.2.21 pypi_0 pypi
[conda] nvidia-cufft-cu12 11.3.3.83 pypi_0 pypi
[conda] nvidia-curand-cu12 10.3.9.90 pypi_0 pypi
[conda] nvidia-cusolver-cu12 11.7.3.90 pypi_0 pypi
[conda] nvidia-cusparse-cu12 12.5.8.93 pypi_0 pypi
[conda] nvidia-cusparselt-cu12 0.7.1 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.27.5 pypi_0 pypi
[conda] nvidia-nvjitlink-cu12 12.8.93 pypi_0 pypi
[conda] nvidia-nvtx-cu12 12.8.90 pypi_0 pypi
[conda] optimum-executorch 0.2.0.dev0 pypi_0 pypi
[conda] pytorch-tokenizers 1.0.1 pypi_0 pypi
[conda] torch 2.9.1 pypi_0 pypi
[conda] torchao 0.14.1+cu129 pypi_0 pypi
[conda] triton 3.5.1 pypi_0 pypi