{ai}[foss/2023b] PyTorch v2.3.0

easybuild/easyconfigs/p/PyTorch/PyTorch-2.3.0-foss-2023b.eb

@@ -0,0 +1,191 @@
+name = 'PyTorch'
+version = '2.3.0'
+
+homepage = 'https://pytorch.org/'
+description = """Tensors and Dynamic neural networks in Python with strong GPU acceleration.
+PyTorch is a deep learning framework that puts Python first."""
+
+toolchain = {'name': 'foss', 'version': '2023b'}
+
+source_urls = [GITHUB_RELEASE]
+sources = ['%(namelower)s-v%(version)s.tar.gz']
+patches = [
+    'PyTorch-1.7.0_disable-dev-shm-test.patch',
+    'PyTorch-1.12.1_add-hypothesis-suppression.patch',
+    'PyTorch-1.12.1_fix-test_cpp_extensions_jit.patch',
+    'PyTorch-1.12.1_fix-TestTorch.test_to.patch',
+    'PyTorch-1.12.1_skip-test_round_robin.patch',
+    'PyTorch-1.13.1_fix-gcc-12-warning-in-fbgemm.patch',
+    'PyTorch-1.13.1_fix-protobuf-dependency.patch',
+    'PyTorch-1.13.1_fix-warning-in-test-cpp-api.patch',
+    'PyTorch-1.13.1_skip-failing-singular-grad-test.patch',
+    'PyTorch-1.13.1_skip-tests-without-fbgemm.patch',
+    'PyTorch-2.0.1_avoid-test_quantization-failures.patch',
+    'PyTorch-2.0.1_fix-skip-decorators.patch',
+    'PyTorch-2.0.1_fix-vsx-loadu.patch',
+    'PyTorch-2.0.1_skip-failing-gradtest.patch',
+    'PyTorch-2.0.1_skip-test_shuffle_reproducibility.patch',
+    'PyTorch-2.0.1_skip-tests-skipped-in-subprocess.patch',
+    'PyTorch-2.1.0_fix-vsx-vector-shift-functions.patch',
+    'PyTorch-2.1.0_increase-tolerance-functorch-test_vmapvjpvjp.patch',
+    'PyTorch-2.1.0_remove-test-requiring-online-access.patch',
+    'PyTorch-2.1.0_skip-diff-test-on-ppc.patch',
+    'PyTorch-2.1.0_skip-dynamo-test_predispatch.patch',
+    'PyTorch-2.1.0_skip-test_jvp_linalg_det_singular.patch',
+    'PyTorch-2.1.2_skip-cpu_repro-test-without-vectorization.patch',
+    'PyTorch-2.1.2_workaround_dynamo_failure_without_nnpack.patch',
+    'PyTorch-2.3.0_disable_test_linear_package_if_no_half_types_are_available.patch',
+    'PyTorch-2.3.0_disable_DataType_dependent_test_if_tensorboard_is_not_available.patch',
+    'PyTorch-2.3.0_skip-test_init_from_local_shards.patch',
+    'PyTorch-2.3.0_no-cuda-stubs-rpath.patch',
+    'PyTorch-2.3.0_disable-gcc12-warning.patch',
+    'PyTorch-2.3.0_fix-test_extension_backend-without-vectorization.patch',
+    'PyTorch-2.3.0_disable_tests_which_need_network_download.patch',
+    'PyTorch-2.3.0_avoid_caffe2_test_cpp_jit.patch',
+    'PyTorch-2.3.0_fix_missing_masked_load_for_int_type.patch',
+    'PyTorch-2.3.0_skip_test_var_mean_differentiable.patch',
+    'PyTorch-2.3.0_skip_test_sdpa_nn_functional_scaled_dot_product_attention_cpu.patch',
+    'PyTorch-2.3.0_fix-mkldnn-avx512-f32-bias.patch',
+]
+checksums = [
+    {'pytorch-v2.3.0.tar.gz': '69579513b26261bbab32e13b7efc99ad287fcf3103087f2d4fdf1adacd25316f'},
+    {'PyTorch-1.7.0_disable-dev-shm-test.patch': '622cb1eaeadc06e13128a862d9946bcc1f1edd3d02b259c56a9aecc4d5406b8a'},
+    {'PyTorch-1.12.1_add-hypothesis-suppression.patch':
+     'e71ffb94ebe69f580fa70e0de84017058325fdff944866d6bd03463626edc32c'},
+    {'PyTorch-1.12.1_fix-test_cpp_extensions_jit.patch':
+     '1efc9850c431d702e9117d4766277d3f88c5c8b3870997c9974971bce7f2ab83'},
+    {'PyTorch-1.12.1_fix-TestTorch.test_to.patch': '75f27987c3f25c501e719bd2b1c70a029ae0ee28514a97fe447516aee02b1535'},
+    {'PyTorch-1.12.1_skip-test_round_robin.patch': '63d4849b78605aa088fdff695637d9473ea60dee603a3ff7f788690d70c55349'},
+    {'PyTorch-1.13.1_fix-gcc-12-warning-in-fbgemm.patch':
+     '5c7be91a6096083a0b1315efe0001537499c600f1f569953c6a2c7f4cc1d0910'},
+    {'PyTorch-1.13.1_fix-protobuf-dependency.patch':
+     '8bd755a0cab7233a243bc65ca57c9630dfccdc9bf8c9792f0de4e07a644fcb00'},
+    {'PyTorch-1.13.1_fix-warning-in-test-cpp-api.patch':
+     'bdde0f2105215c95a54de64ec4b1a4520528510663174fef6d5b900eb1db3937'},
+    {'PyTorch-1.13.1_skip-failing-singular-grad-test.patch':
+     '72688a57b2bb617665ad1a1d5e362c5111ae912c10936bb38a089c0204729f48'},
+    {'PyTorch-1.13.1_skip-tests-without-fbgemm.patch':
+     '481e595f673baf8ae58b41697a6792b83048b0264aa79b422f48cd8c22948bb7'},
+    {'PyTorch-2.0.1_avoid-test_quantization-failures.patch':
+     '02e3f47e4ed1d7d6077e26f1ae50073dc2b20426269930b505f4aefe5d2f33cd'},
+    {'PyTorch-2.0.1_fix-skip-decorators.patch': '2039012cef45446065e1a2097839fe20bb29fe3c1dcc926c3695ebf29832e920'},
+    {'PyTorch-2.0.1_fix-vsx-loadu.patch': 'a0ffa61da2d47c6acd09aaf6d4791e527d8919a6f4f1aa7ed38454cdcadb1f72'},
+    {'PyTorch-2.0.1_skip-failing-gradtest.patch': '8030bdec6ba49b057ab232d19a7f1a5e542e47e2ec340653a246ec9ed59f8bc1'},
+    {'PyTorch-2.0.1_skip-test_shuffle_reproducibility.patch':
+     '7047862abc1abaff62954da59700f36d4f39fcf83167a638183b1b7f8fec78ae'},
+    {'PyTorch-2.0.1_skip-tests-skipped-in-subprocess.patch':
+     '166c134573a95230e39b9ea09ece3ad8072f39d370c9a88fb2a1e24f6aaac2b5'},
+    {'PyTorch-2.1.0_fix-vsx-vector-shift-functions.patch':
+     '3793b4b878be1abe7791efcbd534774b87862cfe7dc4774ca8729b6cabb39e7e'},
+    {'PyTorch-2.1.0_increase-tolerance-functorch-test_vmapvjpvjp.patch':
+     'aef38adf1210d0c5455e91d7c7a9d9e5caad3ae568301e0ba9fc204309438e7b'},
+    {'PyTorch-2.1.0_remove-test-requiring-online-access.patch':
+     '35184b8c5a1b10f79e511cc25db3b8a5585a5d58b5d1aa25dd3d250200b14fd7'},
+    {'PyTorch-2.1.0_skip-diff-test-on-ppc.patch': '394157dbe565ffcbc1821cd63d05930957412156cc01e949ef3d3524176a1dda'},
+    {'PyTorch-2.1.0_skip-dynamo-test_predispatch.patch':
+     '6298daf9ddaa8542850eee9ea005f28594ab65b1f87af43d8aeca1579a8c4354'},
+    {'PyTorch-2.1.0_skip-test_jvp_linalg_det_singular.patch':
+     '5229ca88a71db7667a90ddc0b809b2c817698bd6e9c5aaabd73d3173cf9b99fe'},
+    {'PyTorch-2.1.2_skip-cpu_repro-test-without-vectorization.patch':
+     '7ace835af60c58d9e0754a34c19d4b9a0c3a531f19e5d0eba8e2e49206eaa7eb'},
+    {'PyTorch-2.1.2_workaround_dynamo_failure_without_nnpack.patch':
+     'fb96eefabf394617bbb3fbd3a7a7c1aa5991b3836edc2e5d2a30e708bfe49ba1'},
+    {'PyTorch-2.3.0_disable_test_linear_package_if_no_half_types_are_available.patch':
+     '23416f2d9d5226695ec3fbea0671e3650c655c19deefd3f0f8ddab5afa50f485'},
+    {'PyTorch-2.3.0_disable_DataType_dependent_test_if_tensorboard_is_not_available.patch':
+     '0dcbdfde6752c3ff54c5376f521b4a742167669feb7f0f1d4e1d4d55f72b664f'},
+    {'PyTorch-2.3.0_skip-test_init_from_local_shards.patch':
+     '90ed9c2870f57ee6dc032d00873a37e2217a2b92a13035ded1c25ad5306455f2'},
+    {'PyTorch-2.3.0_no-cuda-stubs-rpath.patch':
+     '7ba26824b5def7379cff02ae821a080698e6affea0da45bc846e9ecb89939cb1'},
+    {'PyTorch-2.3.0_disable-gcc12-warning.patch':
+     'a8a624e1a2a5f4c82610173e50bd0f853e49bd5621b432f5aac689f9f6eb1514'},
+    {'PyTorch-2.3.0_fix-test_extension_backend-without-vectorization.patch':
+     '36aa2d5ba175be17f4e996f4fb2d544fe477d4a0bd0644cd59a85063779afc8e'},
+    {'PyTorch-2.3.0_disable_tests_which_need_network_download.patch':
+     'b7fd1a5135dfd4098cdc054182f7bf84a23ac98462a00477712182b5442da855'},
+    {'PyTorch-2.3.0_avoid_caffe2_test_cpp_jit.patch':
+     '041adcd91d994b8c2ab57d227f081cd57e572c157117b37171e1eb8eb576f8fc'},
+    {'PyTorch-2.3.0_fix_missing_masked_load_for_int_type.patch':
+     'aa6ff764f3f7bf84372a8a257fe1b4ae6dc4b9744ad35f0f9015f2696c62a41e'},
+    {'PyTorch-2.3.0_skip_test_var_mean_differentiable.patch':
+     '9703fd0f1fca8916f6d79d83e9a7efe8e3f717362a5fdaa8f5d9da90d0c75018'},
+    {'PyTorch-2.3.0_skip_test_sdpa_nn_functional_scaled_dot_product_attention_cpu.patch':
+     '7955f2655db3da18606574fdcbc5990be24098f49ad1db5e86ea756ea1cc506f'},
+    {'PyTorch-2.3.0_fix-mkldnn-avx512-f32-bias.patch':
+     'ee07d21c3ac7aeb0bd0e39507b18a417b9125284a529102929c4b5c6727c2976'},
+]
+
+osdependencies = [OS_PKG_IBVERBS_DEV]
+
+builddependencies = [
+    ('CMake', '3.27.6'),
+    ('hypothesis', '6.90.0'),
+    # For tests
+    ('pytest-flakefinder', '1.1.0'),
+    ('pytest-rerunfailures', '14.0'),
+    ('pytest-shard', '0.1.2'),
+    ('tlparse', '0.3.5'),
+    ('optree', '0.13.0'),
+    ('unittest-xml-reporting', '3.1.0'),
+]
+
+dependencies = [
+    ('Ninja', '1.11.1'),  # Required for JIT compilation of C++ extensions
+    ('Python', '3.11.5'),
+    ('Python-bundle-PyPI', '2023.10'),
+    ('protobuf', '25.3'),
+    ('protobuf-python', '4.25.3'),
+    ('pybind11', '2.11.1'),
+    ('SciPy-bundle', '2023.11'),
+    ('PyYAML', '6.0.1'),
+    ('MPFR', '4.2.1'),
+    ('GMP', '6.3.0'),
+    ('numactl', '2.0.16'),
+    ('FFmpeg', '6.0'),
+    ('Pillow', '10.2.0'),
+    ('expecttest', '0.2.1'),
+    ('networkx', '3.2.1'),
+    ('sympy', '1.12'),
+    ('Z3', '4.13.0',),
+]
+
+use_pip = True
+buildcmd = '%(python)s setup.py build'  # Run the (long) build in the build step
+
+excluded_tests = {
+    '': [
+        # This test seems to take too long on NVIDIA Ampere at least.
+        'distributed/test_distributed_spawn',
+        # Broken on CUDA 11.6/11.7: https://github.com/pytorch/pytorch/issues/75375
+        'distributions/test_constraints',
+        # no xdoctest
+        'doctests',
+        # failing on broadwell
+        # See https://github.com/easybuilders/easybuild-easyconfigs/issues/17712
+        'test_native_mha',
+        # intermittent failures on various systems
+        # See https://github.com/easybuilders/easybuild-easyconfigs/issues/17712
+        'distributed/rpc/test_tensorpipe_agent',
+        # This test is expected to fail when run in their CI, but won't in our case.
+        # It just checks for a "CI" env variable
+        'test_ci_sanity_check_fail',
+        # This fails consistently and is disabled upstream
+        # See https://github.com/pytorch/pytorch/issues/100152 and
+        # https://github.com/pytorch/pytorch/pull/124712
+        'test_cpp_extensions_open_device_registration',
+
+    ]
+}
+
+local_test_opts = '--continue-through-error --pipe-logs --verbose %(excluded_tests)s'
+runtest = 'cd test && PYTHONUNBUFFERED=1 %(python)s run_test.py ' + local_test_opts
+
+# Especially test_quantization has a few corner cases that are triggered by the random input values,
+# those cannot be easily avoided, see https://github.com/pytorch/pytorch/issues/107030
+# So allow a low number of tests to fail as the tests "usually" succeed
+max_failed_tests = 6
+
+tests = ['PyTorch-check-cpp-extension.py']
+
+moduleclass = 'ai'

easybuild/easyconfigs/p/PyTorch/PyTorch-2.3.0_avoid_caffe2_test_cpp_jit.patch

@@ -0,0 +1,106 @@
+commit 9e09454cdefc14397c57b2435d3da0c0413dbb8e
+Author: Ake Sandgren <ake.sandgren@hpc2n.umu.se>
+Date:   Thu Feb 27 15:18:52 2025 +0100
+
+    Avoid IS_SANDCASTLE tripping on //caffe2/test/cpp/jit:test_custom_class_registrations
+
+diff --git a/test/export/test_export.py b/test/export/test_export.py
+index 9d1006745b4..b7ee8c1d451 100644
+--- a/test/export/test_export.py
++++ b/test/export/test_export.py
+@@ -3917,7 +3917,7 @@ class TestExportCustomClass(TorchTestCase):
+     def setUp(self):
+         if IS_FBCODE:
+             lib_file_path = "//caffe2/test/cpp/jit:test_custom_class_registrations"
+-        elif IS_SANDCASTLE or IS_MACOS:
++        elif False or IS_MACOS:
+             raise unittest.SkipTest("non-portable load_library call used in test")
+         elif IS_WINDOWS:
+             lib_file_path = find_library_location('torchbind_test.dll')
+diff --git a/test/export/test_lift_unlift.py b/test/export/test_lift_unlift.py
+index edbfa0803d4..a93728f8bd3 100644
+--- a/test/export/test_lift_unlift.py
++++ b/test/export/test_lift_unlift.py
+@@ -146,7 +146,7 @@ class TestLift(TestCase):
+     def setUp(self):
+         if IS_MACOS:
+             raise unittest.SkipTest("non-portable load_library call used in test")
+-        elif IS_SANDCASTLE or IS_FBCODE:
++        elif False or IS_FBCODE:
+             torch.ops.load_library(
+                 "//caffe2/test/cpp/jit:test_custom_class_registrations"
+             )
+@@ -379,7 +379,7 @@ class ConstantAttrMapTest(TestCase):
+     def setUp(self):
+         if IS_MACOS:
+             raise unittest.SkipTest("non-portable load_library call used in test")
+-        elif IS_SANDCASTLE or IS_FBCODE:
++        elif False or IS_FBCODE:
+             torch.ops.load_library(
+                 "//caffe2/test/cpp/jit:test_custom_class_registrations"
+             )
+diff --git a/test/export/test_serialize.py b/test/export/test_serialize.py
+index 08381d95b44..59016a874ad 100644
+--- a/test/export/test_serialize.py
++++ b/test/export/test_serialize.py
+@@ -823,7 +823,7 @@ class TestSaveLoad(TestCase):
+ @unittest.skipIf(not torchdynamo.is_dynamo_supported(), "dynamo doesn't support")
+ class TestSerializeCustomClass(TestCase):
+     def setUp(self):
+-        if IS_SANDCASTLE or IS_FBCODE:
++        if False or IS_FBCODE:
+             torch.ops.load_library(
+                 "//caffe2/test/cpp/jit:test_custom_class_registrations"
+             )
+diff --git a/test/export/test_torchbind.py b/test/export/test_torchbind.py
+index 362064812d4..e5b2f4ae511 100644
+--- a/test/export/test_torchbind.py
++++ b/test/export/test_torchbind.py
+@@ -21,7 +21,7 @@ class TestExportTorchbind(TestCase):
+     def setUp(self):
+         if IS_MACOS:
+             raise unittest.SkipTest("non-portable load_library call used in test")
+-        elif IS_SANDCASTLE or IS_FBCODE:
++        elif False or IS_FBCODE:
+             torch.ops.load_library(
+                 "//caffe2/test/cpp/jit:test_custom_class_registrations"
+             )
+diff --git a/test/export/test_unflatten.py b/test/export/test_unflatten.py
+index 64f123136ba..d0baef3777c 100644
+--- a/test/export/test_unflatten.py
++++ b/test/export/test_unflatten.py
+@@ -552,7 +552,7 @@ class TestUnflatten(TestCase):
+     def test_unflatten_constant_obj(self):
+         if IS_MACOS:
+             raise unittest.SkipTest("non-portable load_library call used in test")
+-        elif IS_SANDCASTLE or IS_FBCODE:
++        elif False or IS_FBCODE:
+             torch.ops.load_library(
+                 "//caffe2/test/cpp/jit:test_custom_class_registrations"
+             )
+diff --git a/test/higher_order_ops/test_with_effects.py b/test/higher_order_ops/test_with_effects.py
+index 0c8f12a1058..3347b6ca1fc 100644
+--- a/test/higher_order_ops/test_with_effects.py
++++ b/test/higher_order_ops/test_with_effects.py
+@@ -27,7 +27,7 @@ class TestWithEffects(TestCase):
+     def setUp(self):
+         if IS_MACOS:
+             raise unittest.SkipTest("non-portable load_library call used in test")
+-        elif IS_SANDCASTLE or IS_FBCODE:
++        elif False or IS_FBCODE:
+             torch.ops.load_library(
+                 "//caffe2/test/cpp/jit:test_custom_class_registrations"
+             )
+diff --git a/test/test_weak.py b/test/test_weak.py
+index cc9ff6f58ee..54ee73a6dae 100644
+--- a/test/test_weak.py
++++ b/test/test_weak.py
+@@ -600,7 +600,7 @@ class WeakKeyDictionaryScriptObjectTestCase(TestCase):
+
+     def __init__(self, *args, **kw):
+         unittest.TestCase.__init__(self, *args, **kw)
+-        if IS_SANDCASTLE or IS_FBCODE:
++        if False or IS_FBCODE:
+             torch.ops.load_library(
+                 "//caffe2/test/cpp/jit:test_custom_class_registrations"
+             )

easybuild/easyconfigs/p/PyTorch/PyTorch-2.3.0_disable-gcc12-warning.patch

@@ -0,0 +1,20 @@
+GCC 12 has a false positive warning when compiled for some architectures, e.g. Intel Sapphire Rapids.
+See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=112370
+
+Suppress this warning such that the build doesn't error.
+
+Author: Alexander Grund (TU Dresden)
+
+Ported to 2.3.0, Åke Sandgren
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index b74bf4536f4..bb062fa843a 100644
+--- a/CMakeLists.txt
++++ b/CMakeLists.txt
+@@ -573,6 +573,7 @@ if(MSVC)
+   string(APPEND CMAKE_CXX_FLAGS " /FS")
+   string(APPEND CMAKE_CUDA_FLAGS " -Xcompiler /FS")
+ endif(MSVC)
++append_cxx_flag_if_supported("-Wno-free-nonheap-object" CMAKE_CXX_FLAGS)
+
+ string(APPEND CMAKE_CUDA_FLAGS " -Xfatbin -compress-all")
+