MobileNetv2 FP32 + QS8 Test by mcr229 · Pull Request #82 · pytorch/executorch

mcr229 · 2023-08-19T00:40:01Z

Summary:
Adding some CI for Mobilenetv2.

The test tests for FP32 model and QS8 Model via long term quantization flow.

Differential Revision: D48488928

facebook-github-bot · 2023-08-19T00:40:31Z

This pull request was exported from Phabricator. Differential Revision: D48488928

facebook-github-bot · 2023-08-20T01:05:33Z

This pull request was exported from Phabricator. Differential Revision: D48488928

facebook-github-bot · 2023-08-22T04:33:56Z

This pull request was exported from Phabricator. Differential Revision: D48488928

facebook-github-bot · 2023-08-22T18:40:51Z

This pull request was exported from Phabricator. Differential Revision: D48488928

facebook-github-bot · 2023-08-22T19:38:39Z

This pull request was exported from Phabricator. Differential Revision: D48488928

facebook-github-bot · 2023-08-22T21:31:12Z

This pull request was exported from Phabricator. Differential Revision: D48488928

facebook-github-bot · 2023-08-23T20:33:21Z

This pull request was exported from Phabricator. Differential Revision: D48488928

facebook-github-bot · 2023-08-23T21:17:54Z

This pull request was exported from Phabricator. Differential Revision: D48488928

Summary: Pull Request resolved: pytorch/executorch#66 DQ Linear runtime logic for XNNPACK is FB internal only, so we are adding a flag in the dq linear logic to remove dq linear logic from xnnpack delegate in OSS Differential Revision: D48335277 fbshipit-source-id: eebb6328d9ff0a61f3d0f8875d2e53c6ca0d1989

Differential Revision: D48488930 fbshipit-source-id: 25fe53e0fb8368b23f110886ca87aad24809cc41

Differential Revision: D48488929 fbshipit-source-id: 9077a51786eea69b34aad482bd19c6de33f8b7d5

Summary: Pull Request resolved: pytorch/executorch#82 Adding some CI for Mobilenetv2. The test tests for FP32 model and QS8 Model via long term quantization flow. Reviewed By: digantdesai, larryliu0820, kirklandsign Differential Revision: D48488928 fbshipit-source-id: ef79304baea3fe8441aff23cbc67f066aad376f5

facebook-github-bot · 2023-08-23T22:14:33Z

This pull request was exported from Phabricator. Differential Revision: D48488928

facebook-github-bot · 2023-08-23T23:25:24Z

This pull request has been merged in eaf006e.

Summary: python -m executorch.examples.models.llama2.export_llama --disable_dynamic_shape --qnn --pt2e_quantize qnn_16a4w Segfault error stacktrace ``` [INFO] [Qnn ExecuTorch]: Initialize Qnn backend parameters for Qnn executorch backend type 2 [INFO] [Qnn ExecuTorch]: Caching: Caching is in SAVE MODE. [WARNING] [Qnn ExecuTorch]: Qnn API version 2.19.0 is used. The version is tested against 2.18.0. [INFO] [Qnn ExecuTorch]: Running level=3 optimization. AddressSanitizer:DEADLYSIGNAL ================================================================= ==1523599==ERROR: AddressSanitizer: SEGV on unknown address 0x000000000020 (pc 0x7f1585ee38e2 bp 0x7f16d5ab8800 sp 0x7ffed19ab8b0 T0) ==1523599==The signal is caused by a READ memory access. ==1523599==Hint: address points to the zero page. SCARINESS: 10 (null-deref) #0 0x7f1585ee38e2 (/home/chenlai/fbsource/third-party/qualcomm/qnn/qnn-2.26/lib/x86_64-linux-clang/libQnnHtp.so+0x2ce38e2) (BuildId: bc3ab8ddc89a0e65) #1 0x7f1585dd8926 (/home/chenlai/fbsource/third-party/qualcomm/qnn/qnn-2.26/lib/x86_64-linux-clang/libQnnHtp.so+0x2bd8926) (BuildId: bc3ab8ddc89a0e65) #2 0x7f15844d1161 (/home/chenlai/fbsource/third-party/qualcomm/qnn/qnn-2.26/lib/x86_64-linux-clang/libQnnHtp.so+0x12d1161) (BuildId: bc3ab8ddc89a0e65) #3 0x7f15844dcac6 (/home/chenlai/fbsource/third-party/qualcomm/qnn/qnn-2.26/lib/x86_64-linux-clang/libQnnHtp.so+0x12dcac6) (BuildId: bc3ab8ddc89a0e65) #4 0x7f15844d245b (/home/chenlai/fbsource/third-party/qualcomm/qnn/qnn-2.26/lib/x86_64-linux-clang/libQnnHtp.so+0x12d245b) (BuildId: bc3ab8ddc89a0e65) #5 0x7f15b9bc7b21 in auto torch::executor::qnn::QnnInterface::qnn_backend_validate_op_config<void*, Qnn_OpConfig_t>(void*, Qnn_OpConfig_t) const fbcode/executorch/backends/qualcomm/runtime/backends/QnnFunctionInterface.h:39 pytorch#6 0x7f15b9bc7682 in torch::executor::qnn::QnnBackend::BackendValidateOpConfig(Qnn_OpConfig_t const&) fbcode/executorch/backends/qualcomm/runtime/backends/QnnBackendCommon.h:41 pytorch#7 0x7f15b9bc7115 in torch::executor::qnn::QnnManager::IsNodeSupportedByBackend(std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&) fbcode/executorch/backends/qualcomm/runtime/QnnManager.cpp:450 pytorch#8 0x7f15b9dd44ee in torch::executor::qnn::PyQnnManager::IsNodeSupportedByBackend(std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&) fbcode/executorch/backends/qualcomm/aot/python/PyQnnManagerAdaptor.h:57 pytorch#9 0x7f15b9e5b986 in pybind11::cpp_function::cpp_function<bool, torch::executor::qnn::PyQnnManager, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&, pybind11::name, pybind11::is_method, pybind11::sibling>(bool (torch::executor::qnn::PyQnnManager::*)(std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&), pybind11::name const&, pybind11::is_method const&, pybind11::sibling const&)::'lambda'(torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&)::operator()(torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&) const fbsource/pybind11/pybind11.h:84 pytorch#10 0x7f15b9e5b8b5 in bool pybind11::detail::argument_loader<torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&>::call_impl<bool, pybind11::cpp_function::cpp_function<bool, torch::executor::qnn::PyQnnManager, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&, pybind11::name, pybind11::is_method, pybind11::sibling>(bool (torch::executor::qnn::PyQnnManager::*)(std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&), pybind11::name const&, pybind11::is_method const&, pybind11::sibling const&)::'lambda'(torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&)&, 0ul, 1ul, pybind11::detail::void_type>(torch::executor::qnn::PyQnnManager&&, std::integer_sequence<unsigned long, 0ul, 1ul>, pybind11::detail::void_type&&) && fbsource/pybind11/cast.h:2042 pytorch#11 0x7f15b9e53831 in std::enable_if<!std::is_void<bool>::value, bool>::type pybind11::detail::argument_loader<torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&>::call<bool, pybind11::detail::void_type, pybind11::cpp_function::cpp_function<bool, torch::executor::qnn::PyQnnManager, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&, pybind11::name, pybind11::is_method, pybind11::sibling>(bool (torch::executor::qnn::PyQnnManager::*)(std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&), pybind11::name const&, pybind11::is_method const&, pybind11::sibling const&)::'lambda'(torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&)&>(pybind11::cpp_function::cpp_function<bool, torch::executor::qnn::PyQnnManager, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&, pybind11::name, pybind11::is_method, pybind11::sibling>(bool (torch::executor::qnn::PyQnnManager::*)(std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&), pybind11::name const&, pybind11::is_method const&, pybind11::sibling const&)::'lambda'(torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&)&) && fbsource/pybind11/cast.h:2014 pytorch#12 0x7f15b9e53454 in void pybind11::cpp_function::initialize<pybind11::cpp_function::cpp_function<bool, torch::executor::qnn::PyQnnManager, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&, pybind11::name, pybind11::is_method, pybind11::sibling>(bool (torch::executor::qnn::PyQnnManager::*)(std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&), pybind11::name const&, pybind11::is_method const&, pybind11::sibling const&)::'lambda'(torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&), bool, torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&, pybind11::name, pybind11::is_method, pybind11::sibling>(bool&&, torch::executor::qnn::PyQnnManager (*)(std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&), pybind11::name const&, pybind11::is_method const&, pybind11::sibling const&)::'lambda'(pybind11::detail::function_call&)::operator()(pybind11::detail::function_call&) const fbsource/pybind11/pybind11.h:193 pytorch#13 0x7f15b9e530d3 in void pybind11::cpp_function::initialize<pybind11::cpp_function::cpp_function<bool, torch::executor::qnn::PyQnnManager, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&, pybind11::name, pybind11::is_method, pybind11::sibling>(bool (torch::executor::qnn::PyQnnManager::*)(std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&), pybind11::name const&, pybind11::is_method const&, pybind11::sibling const&)::'lambda'(torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&), bool, torch::executor::qnn::PyQnnManager*, std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&, pybind11::name, pybind11::is_method, pybind11::sibling>(bool&&, torch::executor::qnn::PyQnnManager (*)(std::vector<std::shared_ptr<torch::executor::qnn::OpWrapper>, std::allocator<std::shared_ptr<torch::executor::qnn::OpWrapper>>>&), pybind11::name const&, pybind11::is_method const&, pybind11::sibling const&)::'lambda'(pybind11::detail::function_call&)::__invoke(pybind11::detail::function_call&) fbsource/pybind11/pybind11.h:170 pytorch#14 0x7f15b9d8f707 in pybind11::cpp_function::dispatcher(_object*, _object*, _object*) fbsource/pybind11/pybind11.h:767 pytorch#15 0x327141 in cfunction_call(_object*, _object*, _object*) (.__uniq.281047882695835599676768160755749362799) (/usr/local/fbcode/platform010/bin/python3.10+0x327141) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#16 0x349630 in _PyObject_MakeTpCall (/usr/local/fbcode/platform010/bin/python3.10+0x349630) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#17 0x5897d4 in method_vectorcall(_object*, _object* const*, unsigned long, _object*) (.__uniq.243338978568352371442406765225626566013.llvm.6236606370933165261) (/usr/local/fbcode/platform010/bin/python3.10+0x5897d4) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#18 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#19 0x331421 in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x331421) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#20 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#21 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#22 0x3313f2 in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3313f2) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#23 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#24 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#25 0x3313f2 in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3313f2) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#26 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#27 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#28 0x3313f2 in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3313f2) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#29 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#30 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#31 0x331577 in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x331577) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#32 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#33 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#34 0x3313f2 in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3313f2) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#35 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#36 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#37 0x3313f2 in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3313f2) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#38 0x39b8ca in _PyEval_Vector (/usr/local/fbcode/platform010/bin/python3.10+0x39b8ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#39 0x39ad7d in _PyObject_FastCallDictTstate (/usr/local/fbcode/platform010/bin/python3.10+0x39ad7d) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#40 0x3c8b72 in slot_tp_call(_object*, _object*, _object*) (.__uniq.235726554139783955843240177532338160225) (/usr/local/fbcode/platform010/bin/python3.10+0x3c8b72) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#41 0x392ca8 in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x392ca8) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#42 0x3314ca in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3314ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#43 0x39b8ca in _PyEval_Vector (/usr/local/fbcode/platform010/bin/python3.10+0x39b8ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#44 0x331b18 in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x331b18) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#45 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#46 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#47 0x3314ca in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3314ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#48 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#49 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#50 0x3313f2 in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3313f2) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#51 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#52 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#53 0x3313f2 in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3313f2) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#54 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#55 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#56 0x3314ca in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3314ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#57 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#58 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#59 0x3314ca in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3314ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#60 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#61 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#62 0x3314ca in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3314ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#63 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#64 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#65 0x3314ca in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3314ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#66 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#67 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#68 0x3314ca in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3314ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#69 0x327547 in _PyFunction_Vectorcall (/usr/local/fbcode/platform010/bin/python3.10+0x327547) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#70 0x3928df in call_function(_ts*, PyTraceInfo*, _object***, long, _object*) (.__uniq.79849310599369217189729546442812793949) (/usr/local/fbcode/platform010/bin/python3.10+0x3928df) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#71 0x3314ca in _PyEval_EvalFrameDefault (/usr/local/fbcode/platform010/bin/python3.10+0x3314ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#72 0x39b8ca in _PyEval_Vector (/usr/local/fbcode/platform010/bin/python3.10+0x39b8ca) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#73 0x431565 in PyEval_EvalCode (/usr/local/fbcode/platform010/bin/python3.10+0x431565) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#74 0x431447 in run_mod(_mod*, _object*, _object*, _object*, PyCompilerFlags*, _arena*) (.__uniq.251861886623903963524397139660542440724.llvm.17622910512627074885) (/usr/local/fbcode/platform010/bin/python3.10+0x431447) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#75 0x4e3054 in pyrun_file(_IO_FILE*, _object*, int, _object*, _object*, int, PyCompilerFlags*) (.__uniq.251861886623903963524397139660542440724) (/usr/local/fbcode/platform010/bin/python3.10+0x4e3054) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#76 0x4e2b54 in _PyRun_SimpleFileObject (/usr/local/fbcode/platform010/bin/python3.10+0x4e2b54) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#77 0x4e28f1 in _PyRun_AnyFileObject (/usr/local/fbcode/platform010/bin/python3.10+0x4e28f1) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#78 0x4d4a54 in Py_RunMain (/usr/local/fbcode/platform010/bin/python3.10+0x4d4a54) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#79 0x4d286b in pymain_main(_PyArgv*) (.__uniq.297908980262787110426434251325078884054) (/usr/local/fbcode/platform010/bin/python3.10+0x4d286b) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#80 0x4d2759 in Py_BytesMain (/usr/local/fbcode/platform010/bin/python3.10+0x4d2759) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) pytorch#81 0x7f19e282c656 in __libc_start_call_main (/usr/local/fbcode/platform010/lib/libc.so.6+0x2c656) (BuildId: 93cdceeb8322234c38e1f2c93ad0ff10c7632fa6) pytorch#82 0x7f19e282c717 in __libc_start_main@GLIBC_2.2.5 (/usr/local/fbcode/platform010/lib/libc.so.6+0x2c717) (BuildId: 93cdceeb8322234c38e1f2c93ad0ff10c7632fa6) pytorch#83 0x553d90 in _start (/usr/local/fbcode/platform010/bin/python3.10+0x553d90) (BuildId: a620038add613fd8585eb50983ca8e455d54738e) AddressSanitizer can not provide additional info. AddressSanitizer: SEGV (/home/chenlai/fbsource/third-party/qualcomm/qnn/qnn-2.26/lib/x86_64-linux-clang/libQnnHtp.so+0x2ce38e2) (BuildId: bc3ab8ddc89a0e65) ==1523599==ABORTING ``` Differential Revision: D63736779

…er of NeutronGraph nodes in model Merge in AITEC/executorch from hotfix/nxf93343/raise-error-when-incorrect-number-of-neutron-graphs to main-nxp * commit 'ee733a1d5713eda8341941113009c7609c2a7a9a': [NO-UPSTREAM] Update/remove failing/non-relevant tests Raise exception when there is incorrect number of NeutronGraph nodes in model

* Support cmake install Allowing parent repo to be able to cmake --target install and then find_package(tokenizers CONFIG) This comes in handy when we want to build tokenizers as an external project or rely on FetchContent. * Enable install * Clean up and fix a bunch * Lint

Handle "<|start_header_id|>{role}<|end_header_id|>"

facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Aug 19, 2023

facebook-github-bot added the fb-exported label Aug 19, 2023

mcr229 force-pushed the export-D48488928 branch from 603f679 to 6086d66 Compare August 20, 2023 01:05

mcr229 force-pushed the export-D48488928 branch from 6086d66 to c340e55 Compare August 22, 2023 04:34

mcr229 force-pushed the export-D48488928 branch from c340e55 to 8cc0ed1 Compare August 22, 2023 18:40

mcr229 force-pushed the export-D48488928 branch from 8cc0ed1 to 4912281 Compare August 22, 2023 19:38

mcr229 force-pushed the export-D48488928 branch from 4912281 to 5de77ef Compare August 22, 2023 21:31

mcr229 force-pushed the export-D48488928 branch from 5de77ef to de4911c Compare August 23, 2023 20:33

mcr229 force-pushed the export-D48488928 branch from de4911c to e6af079 Compare August 23, 2023 21:18

mcr229 and others added 4 commits August 23, 2023 15:12

fix permute copy name

ef8bb09

Differential Revision: D48488930 fbshipit-source-id: 25fe53e0fb8368b23f110886ca87aad24809cc41

Fix Long Term Quant Testing

d2d1674

Differential Revision: D48488929 fbshipit-source-id: 9077a51786eea69b34aad482bd19c6de33f8b7d5

mcr229 force-pushed the export-D48488928 branch from e6af079 to c85f0de Compare August 23, 2023 22:14

facebook-github-bot closed this in eaf006e Aug 23, 2023

facebook-github-bot added the Merged label Aug 23, 2023

kirklandsign added a commit that referenced this pull request Jan 14, 2026

Android llama demo skip special tokens (#82)

22af58c

Handle "<|start_header_id|>{role}<|end_header_id|>"

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

MobileNetv2 FP32 + QS8 Test#82

MobileNetv2 FP32 + QS8 Test#82
mcr229 wants to merge 4 commits intopytorch:mainfrom
mcr229:export-D48488928

mcr229 commented Aug 19, 2023

Uh oh!

facebook-github-bot commented Aug 19, 2023

Uh oh!

facebook-github-bot commented Aug 20, 2023

Uh oh!

facebook-github-bot commented Aug 22, 2023

Uh oh!

facebook-github-bot commented Aug 22, 2023

Uh oh!

facebook-github-bot commented Aug 22, 2023

Uh oh!

facebook-github-bot commented Aug 22, 2023

Uh oh!

facebook-github-bot commented Aug 23, 2023

Uh oh!

facebook-github-bot commented Aug 23, 2023

Uh oh!

facebook-github-bot commented Aug 23, 2023

Uh oh!

facebook-github-bot commented Aug 23, 2023

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

mcr229 commented Aug 19, 2023

Uh oh!

facebook-github-bot commented Aug 19, 2023

Uh oh!

facebook-github-bot commented Aug 20, 2023

Uh oh!

facebook-github-bot commented Aug 22, 2023

Uh oh!

facebook-github-bot commented Aug 22, 2023

Uh oh!

facebook-github-bot commented Aug 22, 2023

Uh oh!

facebook-github-bot commented Aug 22, 2023

Uh oh!

facebook-github-bot commented Aug 23, 2023

Uh oh!

facebook-github-bot commented Aug 23, 2023

Uh oh!

facebook-github-bot commented Aug 23, 2023

Uh oh!

facebook-github-bot commented Aug 23, 2023

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants