Skip to content

[Huggingface] Tracing errors led by neuron sdk 2.27.0 #1265

New issue
New issue
Open
Open
[Huggingface] Tracing errors led by neuron sdk 2.27.0#1265
Labels
Inf2bugSomething isn't workinginference
@JingyaHuang

Description

@JingyaHuang
JingyaHuang
opened on Jan 7, 2026

Describe the bug

We observed the support of some models in Optimum Neuron is broken after upgrading to neuron sdk 2.27.0.

ref. huggingface/optimum-neuron#1053

  • Segmentation faults happened during the tracing stage: yolos, wav2vec2, convbert
log 
============================= test session starts ==============================
platform linux -- Python 3.10.12, pytest-8.0.0, pluggy-1.6.0
rootdir: /home/runner/_work/optimum-neuron/optimum-neuron/tests
configfile: pytest.ini
plugins: anyio-4.12.1, timeout-2.4.0, rerunfailures-16.1, forked-1.6.0
collected 143 items / 94 deselected / 49 selected

tests/inference/transformers/test_modeling.py .......................... [ 53%]
Fatal Python error: Segmentation fault

Thread 0x00007f3ee7fff640 (most recent call first):
  File "/usr/lib/python3.10/threading.py", line 324 in wait
  File "/usr/lib/python3.10/threading.py", line 607 in wait
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/tqdm/_monitor.py", line 60 in run
  File "/usr/lib/python3.10/threading.py", line 1016 in _bootstrap_inner
  File "/usr/lib/python3.10/threading.py", line 973 in _bootstrap

Thread 0x00007f3e635fe640 (most recent call first):
  File "/usr/lib/python3.10/threading.py", line 324 in wait
  File "/usr/lib/python3.10/threading.py", line 607 in wait
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/tqdm/_monitor.py", line 60 in run
  File "/usr/lib/python3.10/threading.py", line 1016 in _bootstrap_inner
  File "/usr/lib/python3.10/threading.py", line 973 in _bootstrap

Thread 0x00007f3f7bfff640 (most recent call first):
  File "/usr/lib/python3.10/threading.py", line 324 in wait
  File "/usr/lib/python3.10/threading.py", line 607 in wait
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/tqdm/_monitor.py", line 60 in run
  File "/usr/lib/python3.10/threading.py", line 1016 in _bootstrap_inner
  File "/usr/lib/python3.10/threading.py", line 973 in _bootstrap

Thread 0x00007f43623b6000 (most recent call first):
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/functional.py", line 4788 in interpolate
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/transformers/models/yolos/modeling_yolos.py", line 140 in forward
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1784 in _call_impl
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1773 in _wrapped_call_impl
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/transformers/models/yolos/modeling_yolos.py", line 111 in forward
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1784 in _call_impl
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1773 in _wrapped_call_impl
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/transformers/models/yolos/modeling_yolos.py", line 536 in forward
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/transformers/utils/generic.py", line 1072 in wrapper
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1784 in _call_impl
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1773 in _wrapped_call_impl
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/transformers/models/yolos/modeling_yolos.py", line 671 in forward
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/transformers/utils/generic.py", line 918 in wrapper
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1784 in _call_impl
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1773 in _wrapped_call_impl
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/optimum/exporters/neuron/base.py", line 449 in forward
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1784 in _call_impl
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1773 in _wrapped_call_impl
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch_neuronx/xla_impl/hlo_conversion.py", line 387 in _xla_trace
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch_neuronx/xla_impl/hlo_conversion.py", line 601 in xla_trace
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch_neuronx/xla_impl/trace.py", line 460 in generate_hlo
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch_neuronx/xla_impl/trace.py", line 676 in _trace
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/torch_neuronx/xla_impl/trace.py", line 606 in trace
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/optimum/exporters/neuron/convert.py", line 727 in trace_neuronx
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/optimum/exporters/neuron/convert.py", line 557 in export_neuronx
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/optimum/exporters/neuron/convert.py", line 450 in export
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/optimum/exporters/neuron/convert.py", line 366 in export_models
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/optimum/exporters/neuron/__main__.py", line 663 in main_export
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/optimum/neuron/modeling_traced.py", line 377 in _export
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/optimum/modeling_base.py", line 407 in from_pretrained
  File "/home/runner/_work/optimum-neuron/optimum-neuron/tests/inference/inference_utils.py", line 141 in _setup
  File "/home/runner/_work/optimum-neuron/optimum-neuron/tests/inference/transformers/test_modeling.py", line 1189 in _run_compare_to_transformers
  File "/home/runner/_work/optimum-neuron/optimum-neuron/tests/inference/transformers/test_modeling.py", line 1205 in test_compare_to_transformers_dyn_bs
  File "/usr/lib/python3.10/unittest/case.py", line 549 in _callTestMethod
  File "/usr/lib/python3.10/unittest/case.py", line 591 in run
  File "/usr/lib/python3.10/unittest/case.py", line 650 in __call__
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/unittest.py", line 333 in runtest
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/runner.py", line 173 in pytest_runtest_call
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/runner.py", line 266 in <lambda>
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/runner.py", line 345 in from_call
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/runner.py", line 265 in call_runtest_hook
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/runner.py", line 226 in call_and_report
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/runner.py", line 133 in runtestprotocol
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/runner.py", line 114 in pytest_runtest_protocol
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/main.py", line 351 in pytest_runtestloop
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/main.py", line 326 in _main
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/main.py", line 272 in wrap_session
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/main.py", line 319 in pytest_cmdline_main
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/config/__init__.py", line 174 in main
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/lib/python3.10/site-packages/_pytest/config/__init__.py", line 197 in console_main
  File "/home/runner/_work/optimum-neuron/optimum-neuron/aws_neuron_venv_pytorch/bin/pytest", line 7 in <module>

Extension modules: charset_normalizer.md, requests.packages.charset_normalizer.md, requests.packages.chardet.md, yaml._yaml, regex._regex, numpy.core._multiarray_umath, numpy.core._multiarray_tests, numpy.linalg._umath_linalg, numpy.fft._pocketfft_internal, numpy.random._common, numpy.random.bit_generator, numpy.random._bounded_integers, numpy.random._mt19937, numpy.random.mtrand, numpy.random._philox, numpy.random._pcg64, numpy.random._sfc64, numpy.random._generator, torch._C, torch._C._dynamo.autograd_compiler, torch._C._dynamo.eval_frame, torch._C._dynamo.guards, torch._C._dynamo.utils, torch._C._fft, torch._C._linalg, torch._C._nested, torch._C._nn, torch._C._sparse, torch._C._special, markupsafe._speedups, PIL._imaging, sklearn.__check_build._check_build, scipy._lib._ccallback_c, scipy.sparse._sparsetools, _csparsetools, scipy.sparse._csparsetools, scipy.linalg._fblas, scipy.linalg._flapack, scipy.linalg.cython_lapack, scipy.linalg._cythonized_array_utils, scipy.linalg._solve_toeplitz, scipy.linalg._flinalg, scipy.linalg._decomp_lu_cython, scipy.linalg._matfuncs_sqrtm_triu, scipy.linalg.cython_blas, scipy.linalg._matfuncs_expm, scipy.linalg._decomp_update, scipy.sparse.linalg._dsolve._superlu, scipy.sparse.linalg._eigen.arpack._arpack, scipy.sparse.csgraph._tools, scipy.sparse.csgraph._shortest_path, scipy.sparse.csgraph._traversal, scipy.sparse.csgraph._min_spanning_tree, scipy.sparse.csgraph._flow, scipy.sparse.csgraph._matching, scipy.sparse.csgraph._reordering, psutil._psutil_linux, scipy.special._ufuncs_cxx, scipy.special._ufuncs, scipy.special._specfun, scipy.special._comb, scipy.special._ellip_harm_2, scipy.spatial._ckdtree, scipy._lib.messagestream, scipy.spatial._qhull, scipy.spatial._voronoi, scipy.spatial._distance_wrap, scipy.spatial._hausdorff, scipy.spatial.transform._rotation, scipy.ndimage._nd_image, _ni_label, scipy.ndimage._ni_label, scipy.optimize._minpack2, scipy.optimize._group_columns, scipy.optimize._trlib._trlib, scipy.optimize._lbfgsb, _moduleTNC, scipy.optimize._moduleTNC, scipy.optimize._cobyla, scipy.optimize._slsqp, scipy.optimize._minpack, scipy.optimize._lsq.givens_elimination, scipy.optimize._zeros, scipy.optimize._highs.cython.src._highs_wrapper, scipy.optimize._highs._highs_wrapper, scipy.optimize._highs.cython.src._highs_constants, scipy.optimize._highs._highs_constants, scipy.linalg._interpolative, scipy.optimize._bglu_dense, scipy.optimize._lsap, scipy.optimize._direct, scipy.integrate._odepack, scipy.integrate._quadpack, scipy.integrate._vode, scipy.integrate._dop, scipy.integrate._lsoda, scipy.special.cython_special, scipy.stats._stats, scipy.stats.beta_ufunc, scipy.stats._boost.beta_ufunc, scipy.stats.binom_ufunc, scipy.stats._boost.binom_ufunc, scipy.stats.nbinom_ufunc, scipy.stats._boost.nbinom_ufunc, scipy.stats.hypergeom_ufunc, scipy.stats._boost.hypergeom_ufunc, scipy.stats.ncf_ufunc, scipy.stats._boost.ncf_ufunc, scipy.stats.ncx2_ufunc, scipy.stats._boost.ncx2_ufunc, scipy.stats.nct_ufunc, scipy.stats._boost.nct_ufunc, scipy.stats.skewnorm_ufunc, scipy.stats._boost.skewnorm_ufunc, scipy.stats.invgauss_ufunc, scipy.stats._boost.invgauss_ufunc, scipy.interpolate._fitpack, scipy.interpolate.dfitpack, scipy.interpolate._bspl, scipy.interpolate._ppoly, scipy.interpolate.interpnd, scipy.interpolate._rbfinterp_pythran, scipy.interpolate._rgi_cython, scipy.stats._biasedurn, scipy.stats._levy_stable.levyst, scipy.stats._stats_pythran, scipy._lib._uarray._uarray, scipy.stats._ansari_swilk_statistics, scipy.stats._sobol, scipy.stats._qmc_cy, scipy.stats._mvn, scipy.stats._rcont.rcont, scipy.stats._unuran.unuran_wrapper, pyarrow.lib, pandas._libs.tslibs.ccalendar, pandas._libs.tslibs.np_datetime, pandas._libs.tslibs.dtypes, pandas._libs.tslibs.base, pandas._libs.tslibs.nattype, pandas._libs.tslibs.timezones, pandas._libs.tslibs.fields, pandas._libs.tslibs.timedeltas, pandas._libs.tslibs.tzconversion, pandas._libs.tslibs.timestamps, pandas._libs.properties, pandas._libs.tslibs.offsets, pandas._libs.tslibs.strptime, pandas._libs.tslibs.parsing, pandas._libs.tslibs.conversion, pandas._libs.tslibs.period, pandas._libs.tslibs.vectorized, pandas._libs.ops_dispatch, pandas._libs.missing, pandas._libs.hashtable, pandas._libs.algos, pandas._libs.interval, pandas._libs.lib, pyarrow._compute, pandas._libs.ops, pandas._libs.hashing, pandas._libs.arrays, pandas._libs.tslib, pandas._libs.sparse, pandas._libs.internals, pandas._libs.indexing, pandas._libs.index, pandas._libs.writers, pandas._libs.join, pandas._libs.window.aggregations, pandas._libs.window.indexers, pandas._libs.reshape, pandas._libs.groupby, pandas._libs.json, pandas._libs.parsers, pandas._libs.testing, _cyutility, sklearn._cyutility, sklearn.utils._isfinite, sklearn.utils.sparsefuncs_fast, sklearn.utils.murmurhash, sklearn.utils._openmp_helpers, sklearn.metrics.cluster._expected_mutual_info_fast, sklearn.preprocessing._csr_polynomial_expansion, sklearn.preprocessing._target_encoder_fast, sklearn.metrics._dist_metrics, sklearn.metrics._pairwise_distances_reduction._datasets_pair, sklearn.utils._cython_blas, sklearn.metrics._pairwise_distances_reduction._base, sklearn.metrics._pairwise_distances_reduction._middle_term_computer, sklearn.utils._heap, sklearn.utils._sorting, sklearn.metrics._pairwise_distances_reduction._argkmin, sklearn.metrics._pairwise_distances_reduction._argkmin_classmode, sklearn.utils._vector_sentinel, sklearn.metrics._pairwise_distances_reduction._radius_neighbors, sklearn.metrics._pairwise_distances_reduction._radius_neighbors_classmode, sklearn.metrics._pairwise_fast, google._upb._message, neuronxcc.starfish, neuronxcc.starfish.penguin, neuronxcc.starfish.penguin.ir, neuronxcc.starfish.penguin.ir.OptLevel, neuronxcc.nki.compiler.backends.neuron.CompileOpts, neuronxcc.driver, neuronxcc.driver.InstanceFamily, neuronxcc.starfish.penguin.common, neuronxcc.starfish.penguin.typing, neuronxcc.starfish.penguin.ir.forward_decl, neuronxcc.starfish.penguin.ir.AffineExpr, neuronxcc.starfish.penguin.Options, neuronxcc.starfish.support, neuronxcc.starfish.support.LogContext, neuronxcc.starfish.penguin.ir.Value, neuronxcc.starfish.penguin.ir.User, neuronxcc.support.dtype_impl, neuronxcc.starfish.support.dtype, neuronxcc.starfish.penguin.ir.ComputeValue, neuronxcc.starfish.penguin.ir.DebugInfo, neuronxcc.starfish.penguin.CachedObject, neuronxcc.starfish.penguin.ir.Tensor, neuronxcc.starfish.penguin.ir.AffinePredicate, neuronxcc.starfish.penguin.ir.Instruction, neuronxcc.starfish.penguin.ir.Stmt, neuronxcc.starfish.penguin.ir.Module, neuronxcc.starfish.penguin.ir.Dependency, neuronxcc.starfish.penguin.ir.Axis, neuronxcc.starfish.penguin.ir.Function, neuronxcc.starfish.penguin.PersistentCachedObject, neuronxcc.starfish.penguin.SCEV, neuronxcc.starfish.penguin.targets, neuronxcc.starfish.penguin.native_maths, neuronxcc.starfish.penguin.targets.Opcodes, neuronxcc.starfish.penguin.ir.Access, neuronxcc.starfish.penguin.ir.OpaqueAccess, neuronxcc.starfish.penguin.ir.CallOp, neuronxcc.starfish.penguin.ir.OpaqueOp, neuronxcc.starfish.penguin.ir.Operator, neuronxcc.starfish.penguin.ir.Intrinsics, neuronxcc.starfish.penguin.ir.SingleValueTensor, neuronxcc.starfish.penguin.ir.FusionOp, neuronxcc.starfish.penguin.ir.StructuralControlFlow, neuronxcc.starfish.penguin.ir.ScopeRegion, neuronxcc.starfish.penguin.ir.Branch, neuronxcc.starfish.penguin.ir.Barrier, neuronxcc.starfish.penguin.ir.RngOp, neuronxcc.starfish.penguin.ir.DMAQoS, neuronxcc.starfish.penguin.ir.PermuteChainUniqueTensors, neuronxcc.starfish.penguin.ir.DimensionSet, neuronxcc.starfish.penguin.ir.CollectiveOp, neuronxcc.starfish.penguin.ir.BatchNorm, neuronxcc.starfish.penguin.ir.RmsNorm, neuronxcc.starfish.penguin.ir.IndexValue, neuronxcc.starfish.penguin.ir.CustomOp, neuronxcc.starfish.penguin.ir.NativeKernel, neuronxcc.starfish.penguin.ir.StmtMixIn, neuronxcc.starfish.penguin.ir.ir, neuronxcc.driver.metrics.Metric, neuronxcc.driver.metrics.Store, neuronxcc.driver.metrics, neuronxcc.driver.GlobalState, neuronxcc.starfish.penguin.Statistics, neuronxcc.starfish.penguin.IntegerSetAnalysis, neuronxcc.nki.compiler.backends.neuron.dimensions, neuronxcc.starfish.penguin.targets.tonga, neuronxcc.starfish.penguin.targets.tonga.TongaTensor, neuronxcc.starfish.penguin.targets.core_v4, neuronxcc.starfish.penguin.targets.sunda, neuronxcc.starfish.penguin.dtypes, neuronxcc.hwm, neuronxcc.starfish.penguin.targets.tonga.Tonga, neuronxcc.starfish.penguin.targets.sunda.Sunda, neuronxcc.starfish.penguin.targets.cayman, neuronxcc.starfish.penguin.targets.cayman.Cayman, neuronxcc.starfish.penguin.targets.core_v4.CoreV4, neuronxcc.nki.compiler.backends.neuron.metaclasses, neuronxcc.nki.compiler.backends.neuron.nki_ctx, neuronxcc.starfish.penguin.targets.tonga.APIndex, neuronxcc.starfish.penguin.ir.SerializerBase, neuronxcc.starfish.penguin.ordered_set, neuronxcc.starfish.penguin.ir.IRCloner, neuronxcc.starfish.penguin.ir.TileAccess, neuronxcc.logging.ErrorMessages, neuronxcc.logging, neuronxcc.logging.Assert, neuronxcc.driver.TimeRegion, neuronxcc.starfish.penguin.PassConstructor, neuronxcc.starfish.penguin.DAG, neuronxcc.starfish.penguin.ir.Verifier, neuronxcc.starfish.penguin.ir.PaddedTensor, neuronxcc.starfish.penguin.ir.IRBuilder, neuronxcc.starfish.penguin.ir.IRWriter, neuronxcc.starfish.penguin.DotTransform, neuronxcc.starfish.penguin.transforms.DoNothing, neuronxcc.starfish.penguin.transforms.DynamicInstEstimator, neuronxcc.starfish.penguin.transforms.LoopTransformUtils, neuronxcc.starfish.penguin.transforms.CanonicalizeIR, neuronxcc.starfish.penguin.ir.InstUtil, neuronxcc.starfish.penguin.models.utils, neuronxcc.starfish.penguin.models.StableDiffusion, neuronxcc.starfish.penguin.models, neuronxcc.starfish.penguin.transforms.experimental.OperatorFusion, neuronxcc.starfish.penguin.transforms.experimental, neuronxcc.starfish.penguin.transforms.experimental.lnc_sharding_gspmd.Sharding, neuronxcc.starfish.penguin.transforms.experimental.lnc_sharding_gspmd, neuronxcc.starfish.penguin.transforms.DelinearizationBase, neuronxcc.starfish.penguin.transforms.EliminateDivs, neuronxcc.starfish.penguin.transforms.ModDivDelinear, neuronxcc.starfish.penguin.transforms.Delinearization, neuronxcc.starfish.penguin.transforms.TensorOpUtils, neuronxcc.starfish.penguin.transforms.HoistAllGather, neuronxcc.starfish.penguin.transforms.MutateDataType, neuronxcc.starfish.penguin.ir.IRSimulator, neuronxcc.starfish.penguin.transforms.DataflowUtil, neuronxcc.starfish.penguin.IslSimplifier, neuronxcc.starfish.penguin.transforms.LoopFusion, neuronxcc.starfish.penguin.transforms.PatternMatch, neuronxcc.starfish.penguin.transforms.Simplifier, neuronxcc.starfish.penguin.transforms.IPSimplifier, neuronxcc.starfish.penguin.transforms.GenericAccessSimplifier, neuronxcc.starfish.penguin.transforms.ValueNumbering, neuronxcc.starfish.penguin.transforms.DeadStoreElimination, neuronxcc.starfish.penguin.transforms.DeadCodeElimination, neuronxcc.starfish.penguin.transforms.MemcpyElimination, neuronxcc.starfish.penguin.transforms.PadElimination, neuronxcc.starfish.penguin.transforms.SimplifyPredicates, neuronxcc.starfish.penguin.transforms.TensorContract, neuronxcc.starfish.penguin.transforms.LICM, neuronxcc.starfish.penguin.transforms.PerfectLoopNest, neuronxcc.starfish.penguin.transforms.ResolvePredicates, neuronxcc.starfish.penguin.transforms.AffinePredicateResolution, neuronxcc.starfish.penguin.transforms.ResolveComplicatePredicates, neuronxcc.starfish.penguin.transforms.RecognizeOpIdiom, neuronxcc.starfish.penguin.transforms.DetailDynInst, neuronxcc.starfish.penguin.transforms.PrintFunction, neuronxcc.starfish.penguin.transforms.SuperSimplifier, neuronxcc.starfish.penguin.scoped_lru_cache, neuronxcc.starfish.penguin.targets.tonga.TongaTranspose, neuronxcc.starfish.penguin.DFG, neuronxcc.starfish.penguin.transforms.DataflowViewer, neuronxcc.starfish.penguin.transforms.InferIntrinsic, neuronxcc.starfish.penguin.transforms.PredicateAffineSelect, neuronxcc.starfish.penguin.transforms.RangeAnalysis, neuronxcc.starfish.penguin.transforms.MaskPropagation, neuronxcc.starfish.penguin.transforms.FlattenLoop, neuronxcc.starfish.penguin.transforms.SimplifySlice, neuronxcc.starfish.penguin.transforms.TensorOpTransform, neuronxcc.starfish.penguin.transforms.ConcatDelinearizer, neuronxcc.starfish.penguin.transforms.TensorOpSimplifier, neuronxcc.starfish.penguin.transforms.LowerTensorOp, neuronxcc.starfish.penguin.transforms.LateLowerTensorOp, neuronxcc.starfish.penguin.transforms.AliasDependencyInduction, neuronxcc.starfish.penguin.transforms.LegalizeOpLevelAlias, neuronxcc.starfish.penguin.transforms.AliasDependencyElimination, neuronxcc.starfish.penguin.transforms.OptimizeAliasedCopyChain, neuronxcc.starfish.penguin.transforms.LoadStoreDependencyAnalysis, neuronxcc.starfish.penguin.transforms.AliasDependencyVerifier, neuronxcc.starfish.penguin.transforms.AliasDependencyVerificationPass, neuronxcc.starfish.penguin.transforms.AliasDependencyReset, neuronxcc.starfish.penguin.transforms.IPSubgraphTensorAnalysis, neuronxcc.starfish.penguin.ir.FunctionUtil, neuronxcc.starfish.penguin.transforms.TransformMustAlias, neuronxcc.starfish.penguin.transforms.TransposeOpElimination, neuronxcc.starfish.penguin.transforms.ConcatOpElimination, neuronxcc.starfish.penguin.transforms.SliceOpElimination, neuronxcc.starfish.penguin.transforms.ReshapeOpElimination, neuronxcc.starfish.penguin.transforms.CastOpElimination, neuronxcc.starfish.penguin.transforms.AnalyzeKernel, neuronxcc.starfish.penguin.transforms, neuronxcc.starfish.penguin.targets.tonga.TongaMacro, neuronxcc.starfish.penguin.targets.tonga.ResolveTongaMacroPredicates, neuronxcc.starfish.birpy, neuronxcc.generated, neuronxcc.generated.starfish.birpy, neuronxcc.generated.starfish.birpy.Opcodes, neuronxcc.starfish.birpy.Common, neuronxcc.starfish.birpy.BirAxis, neuronxcc.starfish.birpy.BirAffineExpr, neuronxcc.starfish.birpy.AccessPattern, neuronxcc.starfish.birpy.Opcodes, neuronxcc.starfish.birpy.Instruction, neuronxcc.starfish.birpy.InstructionOpcodes, neuronxcc.starfish.penguin.targets.tonga.TongaEnums, neuronxcc.starfish.penguin.targets.generated.TensorCopyBaseGen, neuronxcc.starfish.penguin.targets.generated.TensorCopyOpGen, neuronxcc.starfish.penguin.targets.generated.DMACopyOpGen, neuronxcc.starfish.penguin.targets.generated.InlineASMInstGen, neuronxcc.starfish.penguin.targets.generated.InlineASMBytesInstGen, neuronxcc.starfish.penguin.targets.tonga.TongaInst, neuronxcc.isa_tpb.python, neuronxcc.isa_tpb.python.enum_mapping, neuronxcc.isa_tpb.python.isa_construction_helpers, neuronxcc.starfish.penguin.targets.generated.NeuronReadTensorPtrGen, neuronxcc.starfish.penguin.targets.generated.NeuronDDRInstGen, neuronxcc.starfish.penguin.targets.generated.NeuronIndirectLoadStoreGen, neuronxcc.starfish.penguin.targets.generated.NeuronIndirectLoadGen, neuronxcc.starfish.penguin.targets.generated.NeuronIndirectSaveGen, neuronxcc.starfish.penguin.targets.generated.TensorCopyDynamicBaseGen, neuronxcc.starfish.penguin.targets.generated.TensorCopyDynamicSrcGen, neuronxcc.starfish.penguin.targets.generated.TensorCopyDynamicDstGen, neuronxcc.starfish.penguin.targets.generated.NeuronIndirectRMWGen, neuronxcc.starfish.penguin.targets.generated.SBAtomLoadGen, neuronxcc.starfish.penguin.targets.generated.SBAtomStoreGen, neuronxcc.starfish.penguin.targets.generated.TensorTensorOpGen, neuronxcc.starfish.penguin.targets.generated.TensorReduceOpGen, neuronxcc.starfish.penguin.targets.generated.TransposeBatchnormStats2Gen, neuronxcc.starfish.penguin.targets.generated.TransposeTensorReduceOpGen, neuronxcc.starfish.penguin.targets.generated.PartitionReduceOpGen, neuronxcc.starfish.penguin.targets.sunda.utils.axes_utils, neuronxcc.starfish.penguin.targets.generated.NeuronReduceMacroGen, neuronxcc.starfish.penguin.targets.generated.TensorScalarGEPOpGen, neuronxcc.starfish.penguin.targets.generated.TensorScalarPtrOpGen, neuronxcc.starfish.penguin.targets.generated.TensorScalarCacheCumulativeGen, neuronxcc.starfish.penguin.targets.generated.TensorScalarCacheReduceGen, neuronxcc.starfish.penguin.targets.generated.ReciprocalOpGen, neuronxcc.starfish.penguin.targets.generated.MemsetOpGen, neuronxcc.starfish.penguin.targets.generated.DropoutMaskInstGen, neuronxcc.starfish.penguin.targets.sunda.utils.expr_utils, neuronxcc.starfish.penguin.targets.generated.IndexValueInstGen, neuronxcc.starfish.penguin.targets.generated.AffSelTensorScalarOpGen, neuronxcc.starfish.penguin.targets.generated.ActivationOpGen, neuronxcc.starfish.penguin.targets.generated.ActivationAccumulationOpGen, neuronxcc.starfish.penguin.targets.generated.MatMulOpBaseGen, neuronxcc.starfish.penguin.targets.generated.MatMulOpGen, neuronxcc.starfish.penguin.targets.generated.MatMulSparseOpGen, neuronxcc.starfish.penguin.targets.generated.TransposeOpBaseGen, neuronxcc.starfish.penguin.targets.generated.TransposeOpGen, neuronxcc.starfish.penguin.targets.generated.DMATransposeGen, neuronxcc.starfish.penguin.targets.generated.DMAIndirectTransposeGen, neuronxcc.starfish.penguin.targets.generated.BroadcastPartitionGen, neuronxcc.starfish.penguin.targets.generated.ComplexBroadcastPartitionGen, neuronxcc.starfish.penguin.targets.generated.SimpleBroadcastPartitionGen, neuronxcc.starfish.penguin.targets.generated.ShuffleTInstGen, neuronxcc.starfish.penguin.targets.generated.ParReduceBNMeanVarGen, neuronxcc.starfish.penguin.targets.generated.SundaBNStatsGen, neuronxcc.starfish.penguin.targets.generated.SundaBNAggrGen, neuronxcc.starfish.penguin.targets.generated.SundaBNGradientGen, neuronxcc.starfish.penguin.targets.generated.SundaBNBackpropGen, neuronxcc.starfish.penguin.targets.generated.SundaBNBackprop2Gen, neuronxcc.starfish.penguin.targets.generated.RangeSelectGen, neuronxcc.starfish.penguin.targets.generated.RangeSelectReduceGen, neuronxcc.starfish.penguin.targets.generated.TensorSelectGen, neuronxcc.starfish.penguin.targets.generated.TensorCopyPredicatedGen, neuronxcc.starfish.penguin.targets.generated.SelectReduceGen, neuronxcc.starfish.penguin.targets.generated.CrossQuadrantTensorCopyOpGen, neuronxcc.starfish.penguin.targets.generated.NeuronPrintInstGen, neuronxcc.starfish.penguin.targets.generated.LoadTensorToRegisterGen, neuronxcc.starfish.penguin.targets.generated.GetGlobalRankIdGen, neuronxcc.starfish.penguin.targets.tonga.TongaISAInst, neuronxcc.include.isa, neuronxcc.include.isa.datamodels.fields, neuronxcc.include.isa.datamodels.schema, neuronxcc.include.isa.datamodels.datamodel, neuronxcc.include.isa.datamodels, neuronxcc.include.isa.datamodels.specifications, neuronxcc.include.isa.instruction_info, neuronxcc.nki.compiler.backends.neuron.sema, neuronxcc.generated.nki, neuronxcc.generated.nki.compiler, neuronxcc.generated.nki.compiler.backends, neuronxcc.generated.nki.compiler.backends.neuron, neuronxcc.nki.compiler.backends.neuron.scalar, neuronxcc.nki.compiler.backends.neuron.tensor, neuronxcc.nki.compiler.backends.neuron.scalars, neuronxcc.nki.compiler.backends.neuron.indexing, neuronxcc.nki.compiler.backends.neuron.predicates, neuronxcc.starfish.penguin.targets.generated.SundaSetRandStateGen, neuronxcc.starfish.penguin.targets.generated.SendRecvOpGen, neuronxcc.starfish.penguin.targets.generated.SendRecvCCEOpGen, neuronxcc.starfish.penguin.targets.generated.CoreBarrierOpGen, neuronxcc.starfish.penguin.targets.generated.TiledOffloadedFMAGen, neuronxcc.starfish.penguin.targets.generated.TiledOffloadedMemCpyGen, neuronxcc.starfish.penguin.targets.generated.TiledNativeKernelGen, neuronxcc.starfish.penguin.targets.generated.LNCShuffleOpGen, neuronxcc.starfish.penguin.targets.generated.LocalCollectiveOpGen, neuronxcc.starfish.penguin.targets.generated.LocalReduceOpGen, neuronxcc.starfish.penguin.targets.generated.TiledCollectiveOpGen, neuronxcc.starfish.penguin.targets.generated.TiledAllReduceOpGen, neuronxcc.starfish.penguin.targets.generated.TiledAlltoAllOpGen, neuronxcc.starfish.penguin.targets.generated.TiledAllGatherOpGen, neuronxcc.starfish.penguin.targets.generated.TiledCollectivePermuteOpGen, neuronxcc.starfish.penguin.targets.generated.TiledReduceScatterOpGen, neuronxcc.starfish.penguin.targets.generated.TiledCollectivePermuteReduceOpGen, neuronxcc.starfish.penguin.targets.generated.SundaMax8Gen, neuronxcc.starfish.penguin.targets.generated.SundaMaxIndex8Gen, neuronxcc.starfish.penguin.targets.generated.SundaMatchReplace8Gen, neuronxcc.starfish.penguin.targets.generated.MaxIndexAndMatchReplaceGen, neuronxcc.starfish.penguin.targets.generated.GetSequenceBoundsGen, neuronxcc.starfish.penguin.targets.generated.SundaCustomOpGen, neuronxcc.starfish.penguin.targets.generated.PoolGatherGen, neuronxcc.starfish.penguin.targets.generated.TiledSoftmaxOpGen, neuronxcc.starfish.penguin.targets.generated.TiledSoftmaxExpOpGen, neuronxcc.starfish.penguin.targets.generated.TiledSoftmaxRSumOpGen, neuronxcc.starfish.penguin.targets.generated.TiledSoftmaxDxOpGen, neuronxcc.starfish.penguin.targets.generated.TiledRmsNormOpGen, neuronxcc.starfish.penguin.targets.generated.TensorTensorScanOpGen, neuronxcc.starfish.penguin.targets.generated.IndirectCopyGen, neuronxcc.starfish.penguin.targets.generated.StreamShuffleInstGen, neuronxcc.starfish.penguin.targets.generated.QuantizeMXOpGen, neuronxcc.starfish.penguin.targets.generated.MatMulMXOpGen, neuronxcc.starfish.penguin.targets.generated.ExitOpGen, neuronxcc.starfish.penguin.targets.sunda.SundaISAInst, neuronxcc.nki.compiler.backends.neuron.tensors, neuronxcc.nki.compiler.backends.neuron.LexicalScopeDirective, neuronxcc.nki.compiler.backends.neuron.ImmutableParameter, neuronxcc.starfish.penguin.transforms.AxesGroup, neuronxcc.starfish.penguin.targets.transforms.PGAnalysisHelpers, neuronxcc.starfish.penguin.targets.tonga.DFNLayout, neuronxcc.starfish.penguin.targets.transforms.TargetLowering, neuronxcc.starfish.penguin.models.CNNTraining, neuronxcc.starfish.penguin.targets.transforms.LayoutRequirementAnalysis, neuronxcc.starfish.penguin.targets.transforms.PGAnalysis, neuronxcc.starfish.penguin.targets.transforms.PGAnalysisForTiling, neuronxcc.starfish.penguin.targets.transforms.AGOrderingAnalysis, neuronxcc.starfish.penguin.targets.sunda.Tiling, neuronxcc.starfish.penguin.targets.transforms.TongaIslSimplifier, neuronxcc.starfish.penguin.targets.transforms.TongaLiveInterval, neuronxcc.starfish.penguin.targets.transforms.TensorLiveRange, neuronxcc.starfish.penguin.targets.transforms.AllocateBlocks, neuronxcc.starfish.penguin.targets.transforms.NeuronStackLiveInterval, neuronxcc.starfish.penguin.targets.transforms.StackAllocator, neuronxcc.starfish.penguin.targets.transforms.CachedLiveInterval, neuronxcc.starfish.penguin.targets.transforms.BufferState, neuronxcc.starfish.penguin.targets.transforms.SpillFreeKernel, neuronxcc.starfish.penguin.targets.transforms.AnnotateNoSpill, neuronxcc.starfish.penguin.targets.transforms.LoopTransformUtils, neuronxcc.starfish.penguin.targets.transforms.TongaDelinear, neuronxcc.starfish.penguin.targets.transforms.PGTilingHelpers, neuronxcc.starfish.penguin.networkx_common, neuronxcc.starfish.penguin.targets.transforms.PAGLayoutHelpers, neuronxcc.starfish.penguin.targets.transforms.PartitionVectorization, neuronxcc.starfish.penguin.targets.transforms.BFComputeCutting, neuronxcc.starfish.penguin.targets.transforms.BucketizeCCOp, neuronxcc.starfish.penguin.targets.transforms.DataflowUtils, neuronxcc.starfish.penguin.targets.transforms.FactorizeBlkDims, neuronxcc.starfish.penguin.targets.transforms.TongaLICM, neuronxcc.starfish.penguin.targets.transforms.PartialLoopFusion, neuronxcc.starfish.penguin.targets.transforms.CCOpFusion, neuronxcc.starfish.penguin.ir.UnrollCloner, neuronxcc.starfish.penguin.targets.transforms.InstBuilder, neuronxcc.starfish.penguin.targets.transforms.DTypeMutator, neuronxcc.starfish.penguin.targets.transforms.FlattenAPIndices, neuronxcc.starfish.penguin.targets.transforms.LowerTranspose, neuronxcc.starfish.penguin.targets.transforms.IntrinsicBuilder, neuronxcc.starfish.penguin.targets.tonga.Tiling, neuronxcc.starfish.penguin.targets.transforms.PackParDim, neuronxcc.starfish.penguin.targets.transforms.TongaLoopInterchange, neuronxcc.starfish.penguin.targets.transforms.TongaLoopFusion, neuronxcc.starfish.penguin.targets.transforms.MatMultCombine, neuronxcc.starfish.penguin.targets.transforms.FactorizeFreeDims, neuronxcc.starfish.penguin.targets.transforms.TongaCpyElim, neuronxcc.starfish.penguin.transforms.InstTransformUtils, neuronxcc.starfish.penguin.targets.transforms.TongaInstComb, neuronxcc.starfish.penguin.targets.transforms.LowerIntrinsics, neuronxcc.starfish.penguin.targets.transforms.CoalesceCCOp, neuronxcc.starfish.penguin.targets.transforms.CCOpAxesGroupAnalysis, neuronxcc.starfish.penguin.targets.transforms.MacroGeneration, neuronxcc.starfish.penguin.IslCodeGen, neuronxcc.starfish.penguin.targets.tonga.passes.AutoCastFP32, neuronxcc.starfish.penguin.targets.tonga.passes.TongaLayoutAnalysis, neuronxcc.starfish.penguin.targets.tonga.passes.TransformLayout, neuronxcc.starfish.penguin.targets.tonga.passes.ResolveAccessConflict, neuronxcc.starfish.penguin.targets.tonga.passes.LegalizeTongaMacro, neuronxcc.starfish.penguin.targets.transforms.ShardingUtils, neuronxcc.starfish.penguin.targets.tonga.passes.InferTongaTensor, neuronxcc.starfish.penguin.targets.tonga.passes.TongaSizeTiling, neuronxcc.starfish.penguin.targets.tonga.passes.PartitionLocalityOpt, neuronxcc.starfish.penguin.targets.tonga.LayoutCandidateEnumerator, neuronxcc.starfish.penguin.targets.tonga.LayoutDecisionTree, neuronxcc.starfish.penguin.targets.tonga.passes.GlobalLayoutOpt, neuronxcc.starfish.penguin.targets.tonga.passes.InsertIOTransposes, neuronxcc.starfish.penguin.targets.tonga.passes.TongaISel, neuronxcc.starfish.penguin.targets.tonga.passes.ParLayoutOpt, neuronxcc.starfish.penguin.targets.tonga.passes.WeightCoalescing, neuronxcc.starfish.penguin.targets.tonga.passes.LowerPartitionTile, neuronxcc.starfish.penguin.targets.tonga.passes.LegalizePartitionTile, neuronxcc.starfish.penguin.targets.transforms.SplitAPUnionSets, neuronxcc.starfish.penguin.targets.transforms.RewriteReplicationMatmul, neuronxcc.starfish.penguin.targets.transforms.RewriteWeights, neuronxcc.starfish.penguin.targets.transforms.TongaSimplifyPredicates, neuronxcc.starfish.penguin.targets.transforms.DMALegalizer, neuronxcc.starfish.penguin.targets.tonga.passes.ExpandISAMacro, neuronxcc.starfish.penguin.targets.tonga.passes.UnrollReduceMacro, neuronxcc.starfish.penguin.targets.tonga.passes.TongaValueNumbering, neuronxcc.starfish.penguin.targets.tonga.passes.TongaBufferUsageAnalysis, neuronxcc.starfish.penguin.targets.tonga.passes.StaticProfiler, neuronxcc.starfish.penguin.targets.tonga.passes.FlattenMacroLoop, neuronxcc.starfish.penguin.targets.tonga.passes.ReshapeWeights, neuronxcc.starfish.penguin.targets.transforms.SimplifyTensor, neuronxcc.starfish.penguin.targets.tonga.passes.SimplifyTongaTensor, neuronxcc.starfish.penguin.targets.tonga.passes.LinearizeFreeDim, neuronxcc.starfish.penguin.targets.tonga.passes.SplitFreeDim, neuronxcc.starfish.penguin.targets.tonga.passes.TongaPerfectLoopNest, neuronxcc.starfish.penguin.targets.transforms.Vectorizer, neuronxcc.starfish.penguin.targets.tonga.passes.VectorizeDMA, neuronxcc.starfish.penguin.targets.tonga.passes.BroadcastWeights, neuronxcc.starfish.penguin.targets.tonga.passes.CommuteConcat, neuronxcc.starfish.penguin.targets.tonga.passes.TongaEliminateCasts, neuronxcc.starfish.penguin.targets.tonga.passes.SplitAccGrp, neuronxcc.starfish.penguin.targets.transforms.CycleBasedLayoutCostModel, neuronxcc.starfish.penguin.targets.transforms.PAGLayoutAnalysis, neuronxcc.starfish.penguin.targets.transforms.OperatorLayoutVisualizer, neuronxcc.starfish.penguin.targets.tonga.passes.ParAxesAnnotation, neuronxcc.starfish.penguin.targets.tonga.passes.IPGlobalLayoutOpt, neuronxcc.starfish.penguin.targets.tonga.passes.Recompute, neuronxcc.starfish.penguin.targets.tonga.passes.TilingProfiler, neuronxcc.starfish.penguin.targets.tonga.passes.DMAProfiler, neuronxcc.starfish.penguin.targets.tonga.passes, neuronxcc.starfish.penguin.targets.transforms.DataLocalityOpt, neuronxcc.starfish.penguin.targets.transforms.DataStreaming, neuronxcc.starfish.penguin.targets.transforms.DeConcat, neuronxcc.starfish.penguin.targets.transforms.DMALocalityOpt, neuronxcc.starfish.penguin.targets.transforms.EnforceAluDTAcc, neuronxcc.starfish.penguin.targets.transforms.ExpandBatchNorm, neuronxcc.starfish.penguin.transforms.Region, neuronxcc.starfish.penguin.MCTS, neuronxcc.starfish.penguin.targets.transforms.AllocatorState, neuronxcc.starfish.penguin.targets.transforms.VectorizeLoop, neuronxcc.starfish.penguin.targets.transforms.GlobalSpillCtx, neuronxcc.starfish.penguin.targets.transforms.MaxLiveSpiller, neuronxcc.starfish.penguin.targets.transforms.FastSpillGeneration, neuronxcc.starfish.penguin.targets.transforms.FineGrainedCCOpFusion, neuronxcc.starfish.penguin.targets.transforms.FlattenAxesForTiling, neuronxcc.starfish.penguin.targets.transforms.HoistFSDPCollectives, neuronxcc.starfish.penguin.targets.transforms.AssignDMAQoSLabels, neuronxcc.starfish.penguin.targets.transforms.InferInitValue, neuronxcc.starfish.penguin.targets.transforms.InferNonlocalTensors, neuronxcc.starfish.penguin.targets.transforms.InferPSumTensor, neuronxcc.starfish.penguin.transforms.experimental.lnc_sharding_gspmd.ShardingPropagation, neuronxcc.starfish.penguin.targets.transforms.RemoveShardedPartitionAxes, neuronxcc.starfish.penguin.util, neuronxcc.starfish.penguin.util.model_explorer, neuronxcc.starfish.penguin.util.model_explorer.graph_builder, neuronxcc.starfish.penguin.util.model_explorer.ModelExplorerConverter, neuronxcc.starfish.penguin.targets.transforms.InferShardAxis, neuronxcc.starfish.penguin.targets.transforms.InferSharedMemLoc, neuronxcc.starfish.penguin.targets.sunda.passes.SundaSizeTiling, neuronxcc.starfish.penguin.targets.sunda.passes.LegalizeSundaMacro, neuronxcc.starfish.penguin.targets.sunda.passes.SundaISel, neuronxcc.starfish.penguin.targets.sunda.passes.LegalizePartitionReduce, neuronxcc.starfish.penguin.targets.transforms.LegalizeTongaAccess, neuronxcc.starfish.penguin.targets.sunda.passes.LateLegalizeInst, neuronxcc.starfish.penguin.targets.sunda.passes.InferIntrinsicOnCC, neuronxcc.starfish.penguin.targets.sunda.passes, neuronxcc.starfish.penguin.targets.transforms.experimental.InlineFusionGroup, neuronxcc.starfish.penguin.targets.transforms.experimental.DFSStackAllocator, neuronxcc.starfish.penguin.targets.transforms.experimental.NKITensorCanonicalization, neuronxcc.starfish.penguin.targets.transforms.experimental, neuronxcc.starfish.penguin.targets.transforms.experimental.TongaIslDependenceAnalysis, neuronxcc.starfish.penguin.targets.transforms.SoftwarePipelineCodeGen, neuronxcc.starfish.penguin.targets.transforms.LowerShardAxis, neuronxcc.starfish.penguin.targets.transforms.InlineNKIKernels, neuronxcc.starfish.penguin.targets.transforms.InsertCoreBarrier, neuronxcc.starfish.penguin.targets.transforms.InsertImplicitShardAxis, neuronxcc.starfish.penguin.targets.transforms.ReinsertShardAxis, neuronxcc.starfish.penguin.targets.tonga.passes.InsertLocalTransposes, neuronxcc.starfish.penguin.targets.transforms.CanonicalizeDAG, neuronxcc.starfish.penguin.targets.transforms.RoundtripTranspose, neuronxcc.starfish.penguin.targets.transforms.DramToDramTranspose, neuronxcc.starfish.penguin.targets.transforms.CCOpAxesGroupDelinearizer, neuronxcc.starfish.penguin.targets.transforms.LayoutPreprocessing, neuronxcc.starfish.penguin.targets.transforms.LowerCCOpBlockAxis, neuronxcc.starfish.penguin.targets.transforms.PComputeCutting, neuronxcc.starfish.penguin.targets.transforms.LoopSplitting, neuronxcc.starfish.penguin.targets.transforms.StaticTransposeLocalTensor, neuronxcc.starfish.penguin.targets.transforms.InsertOffloadedTransposes, neuronxcc.starfish.penguin.targets.transforms.LayoutTilingPipeline, neuronxcc.starfish.penguin.targets.transforms.LegalizeCCOpLayout, neuronxcc.starfish.penguin.targets.transforms.LegalizeSundaAccess, neuronxcc.starfish.penguin.targets.transforms.LegalizeType, neuronxcc.starfish.penguin.targets.transforms.LocalLegalizeType, neuronxcc.starfish.penguin.targets.transforms.LocalLayoutOpt, neuronxcc.starfish.penguin.targets.transforms.LowerBroadcast, neuronxcc.starfish.penguin.targets.transforms.LowerToSendRecv, neuronxcc.starfish.penguin.targets.transforms.NKIKernelLayout, neuronxcc.starfish.penguin.PrimeFactorization, neuronxcc.starfish.penguin.targets.transforms.autotune._Compiler, neuronxcc.kra, neuronxcc.kra.profile_lib, neuronxcc.starfish.penguin.targets.transforms.autotune._PerformanceMetric, neuronxcc.starfish.penguin.targets.transforms.autotune._TreeSearch, neuronxcc.starfish.penguin.targets.transforms.autotune._Search, neuronxcc.starfish.penguin.targets.transforms.autotune.Autotuner, neuronxcc.starfish.penguin.targets.transforms.autotune, neuronxcc.starfish.penguin.targets.transforms.VectorizeMatMult, neuronxcc.starfish.penguin.targets.transforms.TritiumFusionBase, neuronxcc.starfish.penguin.targets.transforms.TritiumFusion, neuronxcc.starfish.penguin.targets.transforms.PartialSimdFusion, neuronxcc.starfish.penguin.targets.transforms.TensorInitialization, neuronxcc.starfish.penguin.targets.transforms.RelaxPredicates, neuronxcc.starfish.penguin.targets.transforms.Rematerialization, neuronxcc.starfish.support.AccessPattern, neuronxcc.starfish.penguin.targets.tonga.passes.TongaAccessAnalysis, neuronxcc.starfish.penguin.targets.transforms.AllocationDecision, neuronxcc.starfish.penguin.targets.transforms.ModuloAllocation, neuronxcc.starfish.penguin.targets.transforms.SFKVectorizer, neuronxcc.starfish.penguin.targets.transforms.IntervalMinCut, neuronxcc.starfish.penguin.targets.transforms.SMTAllocator, neuronxcc.starfish.penguin.targets.transforms.SMTAllocationPass, neuronxcc.starfish.penguin.targets.transforms.TensorParallel, neuronxcc.starfish.penguin.targets.transforms.SPMDCodeGen, neuronxcc.starfish.penguin.targets.transforms.SimpleAllReduceTiling, neuronxcc.starfish.penguin.targets.transforms.SimplifyMacroPredicates, neuronxcc.starfish.penguin.targets.transforms.SoftmaxDivisionDelay, neuronxcc.starfish.penguin.targets.transforms.SpillPSum, neuronxcc.starfish.penguin.targets.transforms.SpmdDCE, neuronxcc.starfish.penguin.targets.transforms.TensorLifetimeAnalysis, neuronxcc.starfish.penguin.targets.transforms.TileCCOps, neuronxcc.starfish.penguin.targets.transforms.TongaSimplifier, neuronxcc.starfish.penguin.targets.transforms.TransformConvOp, neuronxcc.starfish.penguin.targets.transforms.UnshardBIRKernelForSimulation, neuronxcc.starfish.penguin.targets.tonga.ISAMapper, neuronxcc.starfish.penguin.targets.transforms.NeuronVerifier, neuronxcc.starfish.penguin.targets.transforms, neuronxcc.nki.compiler.backends.neuron.stmts, neuronxcc.nki.compiler.backends.neuron.allocator, neuronxcc.nki.isa.constants, neuronxcc.include.isa.tensor_scalar_cumulative_info, neuronxcc.include.isa.behavior, neuronxcc.include.isa.behavior.range_select_behavior, neuronxcc.include.isa.range_select_info, neuronxcc.nki.isa.neuron_isa, neuronxcc.nki.isa, neuronxcc.nki.compiler.backends.neuron.AccessBoundChecker, neuronxcc.nki.compiler.backends.neuron.NkiTypeSystemCmpOp, neuronxcc.nki.compiler.backends.neuron.NkiTypeSystemLogicalOp, neuronxcc.nki.compiler.backends.neuron.NkiTypeSystem, neuronxcc.nki.compiler.backends.neuron.TraceContext, neuronxcc.nki.compiler.backends.neuron.KernelBuilder, neuronxcc.generated.nki.compiler.backends.neuron.KernelBuilder, neuronxcc.nki.compiler.backends.neuron.KernelRewriter, neuronxcc.nki.compiler.backends.neuron.TraceKernel, neuronxcc.nki.compiler.backends.neuron.decorators, neuronxcc.nki.compiler, neuronxcc.nki.compiler.backends.neuron.FrameworkKernel, neuronxcc.nki.compiler.backends.neuron.NumpyKernel, neuronxcc.nki.compile, neuronxcc.nki.typing, neuronxcc.nki, neuronxcc.nki.language.memory_ops, neuronxcc.nki.language.creation_ops, neuronxcc.nki.language.iterators, neuronxcc.nki.language.programming_model, neuronxcc.nki.language.shape_manipulation_ops, neuronxcc.nki._private, neuronxcc.nki._private.private_api, neuronxcc.nki.language.math_ops, neuronxcc.nki.language.indexing_ops, neuronxcc.nki.language.debug, neuronxcc.nki.language.constants, neuronxcc.nki.dtype, neuronxcc.nki.language, neuronxcc.nki._torch_xla, pyarrow._parquet, pyarrow._fs, pyarrow._azurefs, pyarrow._hdfs, pyarrow._gcsfs, pyarrow._s3fs, multidict._multidict, yarl._quoting_c, propcache._helpers_c, aiohttp._http_writer, aiohttp._http_parser, aiohttp._websocket.mask, aiohttp._websocket.reader_c, frozenlist._frozenlist, xxhash._xxhash, pyarrow._acero, pyarrow._csv, pyarrow._json, pyarrow._substrait, pyarrow._dataset, pyarrow._dataset_orc, pyarrow._parquet_encryption, pyarrow._dataset_parquet_encryption, pyarrow._dataset_parquet, PIL._imagingft, _cffi_backend, neuronxcc.nki._private_kernels.legacy, neuronxcc.nki._private_kernels.legacy.vision, neuronxcc.nki._private_kernels.legacy.tutorial, neuronxcc.nki._private_kernels.legacy.allocated_fused_linear, neuronxcc.nki.nccl.collectives, neuronxcc.nki.nccl, neuronxcc.nki._private_kernels.blockwise_mm, neuronxcc.nki._private_kernels.router_topk, neuronxcc.nki._private_kernels.shard_common, neuronxcc.nki._private_kernels.mlp, neuronxcc.nki._private_kernels.expert_mlps, sentencepiece._sentencepiece, PIL._imagingmath (total: 791)
/home/runner/_work/_temp/35e6401e-e9a1-4469-a941-f8ad6766fc31.sh: line 3:  7641 Segmentation fault      (core dumped) pytest -m "not slow" tests/inference/transformers/test_modeling.py
..........
Error: Process completed with exit code 139.
  • Tracing also broken for: hubert and cvt
log 
tests/exporters/test_transformers.py:118: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/optimum/exporters/neuron/convert.py:470: in export
    return export_neuronx(
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/optimum/exporters/neuron/convert.py:577: in export_neuronx
    trace_neuronx(
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/optimum/exporters/neuron/convert.py:747: in trace_neuronx
    neuron_model = neuronx.trace(
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch_neuronx/xla_impl/trace.py:606: in trace
    neff_filename, metaneff, flattener, packer, weights = _trace(
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch_neuronx/xla_impl/trace.py:676: in _trace
    hlo_artifacts = generate_hlo(
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch_neuronx/xla_impl/trace.py:460: in generate_hlo
    ) = xla_trace(
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch_neuronx/xla_impl/hlo_conversion.py:601: in xla_trace
    return _xla_trace(func, example_inputs, states, input_output_aliases,
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch_neuronx/xla_impl/hlo_conversion.py:387: in _xla_trace
    outputs = func(*example_inputs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1773: in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1784: in _call_impl
    return forward_call(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/optimum/exporters/neuron/base.py:453: in forward
    outputs = self.model(**ordered_inputs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1773: in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1784: in _call_impl
    return forward_call(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/transformers/models/hubert/modeling_hubert.py:986: in forward
    encoder_outputs = self.encoder(
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1773: in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1784: in _call_impl
    return forward_call(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/transformers/models/hubert/modeling_hubert.py:448: in forward
    position_embeddings = self.pos_conv_embed(hidden_states)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1773: in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1784: in _call_impl
    return forward_call(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/transformers/models/hubert/modeling_hubert.py:92: in forward
    hidden_states = self.conv(hidden_states)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1773: in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1784: in _call_impl
    return forward_call(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/conv.py:371: in forward
    return self._conv_forward(input, self.weight, self.bias)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/utils/parametrize.py:407: in get_parametrized
    return parametrization()
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1773: in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1784: in _call_impl
    return forward_call(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/utils/parametrize.py:303: in forward
    x = self[0](*originals)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1773: in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
../aws_neuron_venv_2.27_2.8/lib/python3.10/site-packages/torch/nn/modules/module.py:1784: in _call_impl
    return forward_call(*args, **kwargs)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = _WeightNorm()
weight_g = Placeholder for tensor([[[0.5981, 0.5571, 0.5722, 0.5887, 0.5778, 0.5980, 0.5492, 0.6171,
          0.5687, 0.5570, 0.5737, 0.5950, 0.6212, 0.5705, 0.5406, 0.5664]]])
weight_v = Placeholder for tensor([[[-0.0074,  0.0228, -0.0304,  ...,  0.0243, -0.0542,  0.0165],
         [-0.0210,  0.0698, -0....83, -0.0439,  ..., -0.0218,  0.0507, -0.0417],
         [ 0.0341,  0.0656,  0.0789,  ..., -0.0154, -0.0302, -0.0750]]])

    def forward(self, weight_g, weight_v):
>       return torch._weight_norm(weight_v, weight_g, self.dim)
E       RuntimeError: torch_xla/csrc/runtime/pjrt_computation_client.cpp:514 : Check failed: pjrt_data->buffer != nullptr 
E       *** Begin stack trace ***
E               tsl::CurrentStackTrace[abi:cxx11]()
E               torch_xla::runtime::PjRtComputationClient::TransferFromDevice(absl::lts_20230802::Span<std::shared_ptr<torch_xla::runtime::ComputationClient::Data> const>)
E               torch_xla::ReleaseGilAndTransferData(absl::lts_20230802::Span<std::shared_ptr<torch::lazy::BackendData> const>)
E               torch_xla::XLAGraphExecutor::GetTensors(std::vector<c10::intrusive_ptr<torch_xla::XLATensor, c10::detail::intrusive_target_default_null_type<torch_xla::XLATensor> >, std::allocator<c10::intrusive_ptr<torch_xla::XLATensor, c10::detail::intrusive_target_default_null_type<torch_xla::XLATensor> > > >*)
E               torch_xla::bridge::XlaCreateTensorList(c10::IListRef<at::Tensor> const&)
E               torch_xla::XLANativeFunctions::_to_cpu(c10::ArrayRef<at::Tensor>)
E       
E               at::_ops::_to_cpu::call(c10::ArrayRef<at::Tensor>)
E       
E               at::native::cpu_fallback(c10::OperatorHandle const&, std::vector<c10::IValue, std::allocator<c10::IValue> >*, bool, c10::DispatchKey)
E               torch_xla::xla_fallback(c10::OperatorHandle const&, std::vector<c10::IValue, std::allocator<c10::IValue> >*)
E               at::_ops::_weight_norm_interface::redispatch(c10::DispatchKeySet, at::Tensor const&, at::Tensor const&, long)
E       
E       
E               at::_ops::_weight_norm_interface::call(at::Tensor const&, at::Tensor const&, long)
E               at::native::_weight_norm(at::Tensor const&, at::Tensor const&, long)
E       
E               at::_ops::_weight_norm::call(at::Tensor const&, at::Tensor const&, long)
E       
E       
E               _PyObject_MakeTpCall
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E               _PyObject_FastCallDictTstate
E               _PyObject_Call_Prepend
E       
E               PyObject_Call
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E               _PyObject_FastCallDictTstate
E               _PyObject_Call_Prepend
E       
E               _PyObject_MakeTpCall
E               _PyEval_EvalFrameDefault
E       
E               _PyObject_GenericGetAttrWithDict
E       
E               PyObject_GetAttr
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E               _PyObject_FastCallDictTstate
E               _PyObject_Call_Prepend
E       
E               _PyObject_MakeTpCall
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E               _PyObject_FastCallDictTstate
E               _PyObject_Call_Prepend
E       
E               _PyObject_MakeTpCall
E               _PyEval_EvalFrameDefault
E       
E               PyObject_Call
E               _PyEval_EvalFrameDefault
E       
E               PyObject_Call
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyObject_FastCallDictTstate
E               _PyObject_Call_Prepend
E       
E               _PyObject_MakeTpCall
E               _PyEval_EvalFrameDefault
E       
E               PyObject_Call
E               _PyEval_EvalFrameDefault
E       
E               PyObject_Call
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyObject_FastCallDictTstate
E               _PyObject_Call_Prepend
E       
E               PyObject_Call
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E               _PyObject_FastCallDictTstate
E               _PyObject_Call_Prepend
E       
E               PyObject_Call
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E       
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyEval_EvalFrameDefault
E       
E               PyObject_Call
E               _PyEval_EvalFrameDefault
E               _PyFunction_Vectorcall
E               _PyObject_FastCallDictTstate
E               _PyObject_Call_Prepend
E       
E               _PyObject_MakeTpCall
E       *** End stack trace ***
E       PjRt buffer is null in TransferFromDevice

Model Name

yolos, wav2vec2, convbert, hubert, cvt

Describe the workload type

Inference

Instance Type

inf2.8xlarge

Release version

aws-neuronx-collectives/unknown,now 2.29.41.0-681fef5f5 amd64 [installed]
aws-neuronx-dkms/unknown,now 2.25.4.0 all [installed]
aws-neuronx-runtime-lib/unknown,now 2.29.40.0-f954cd7a5 amd64 [installed]
aws-neuronx-tools/unknown,now 2.27.33.0-5d9c0b901 amd64 [installed]

Reproduction Steps

Checkout to the main branch of optimum-neuron, and then

pytest tests/exporters/test_transformers.py

and

pytest tests/inference/transformers/test_modeling.py

Regression Issue

  • Select this option if this issue appears to be a regression.

Possible Solution

No response

Logs/Context/Additional Information

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    Inf2bugSomething isn't workinginference

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions