Summary: Since table caffe2_pytorch_usage_stats only has 1 day retention which renders it useless for TS migration purposes, we want to build a lightweight counter mechanism to collect usage data about torch jit APIs which can monitor the usage decline in the long term.
Test Plan: CI
Reviewed By: SherlockNoMad
Differential Revision: D57216847
Pull Request resolved: https://github.com/pytorch/pytorch/pull/125986
Approved by: https://github.com/gmagogsfm
Number of OSS PR were reverted, because new signed-unsigned comparison warnings, which are treated as errors in some internal builds.
Not sure how those selective rules are applied, but this PR removes `-Wno-sign-compare` from PyTorch codebase.
The only tricky part in this PR, as making sure that non-ASCII character detection works for both signed and unsigned chars here:
6e3d51b08a/torch/csrc/jit/serialization/python_print.cpp (L926)
Exclude several files from sign-compare if flash attention is used, due to the violation in cutlass, to be fixed by https://github.com/NVIDIA/cutlass/pull/869
Do not try to fix sign compare violations in caffe2 codebase
Pull Request resolved: https://github.com/pytorch/pytorch/pull/96723
Approved by: https://github.com/albanD
As we live in C++17 world
This is a functional no-op, just
- `s/namespace at { namespace native {/namespace at::native {/`
- `s/namespace torch { namespace jit {/namespace torch::jit {/`
Pull Request resolved: https://github.com/pytorch/pytorch/pull/92100
Approved by: https://github.com/izaitsevfb
Summary:
Remove code dup in import.cpp / export_modules.cpp such that
1. Only one copy of switching logic (detect flatbuffer / is_flatbuffer);
2. Move detection of includeness of flatbuffer to runtime (so no more macros)
This also reverts the dependency of import.cpp -> flatbuffer_loader.cpp to flatbuffer_loader.cpp -> import.cpp.
Differential Revision: D36926217
Pull Request resolved: https://github.com/pytorch/pytorch/pull/79184
Approved by: https://github.com/zhxchen17
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/76164
For the case `Dict[int, Tuple[Tensor, Tensor]]`, the value type is a `Tuple`, and their qualified name should be `(Tensor, Tensor)`. Their definition won't be in compilation unit, but type parse can parse it easily. We can just use the default string `(Tensor, Tensor)` directly.
ghstack-source-id: 154517975
Test Plan:
```
[chenlai@1833.od /data/sandcastle/boxes/fbsource/fbcode (aba59247a|remote/fbcode/warm)]$ buck test //smart/pytorch_mobile/backport_service:handler_test
Starting new Buck daemon...
Buck daemon started.
DEBUG: /data/sandcastle/boxes/fbsource/tools/build_defs/fbcode_macros/build_defs/lib/cpp_common.bzl:287:14: Using disallowed linker flag 'ANativeActivity_onCreate' in library rule 'fbsource//third-party/toolchains/android-ndk:r18b_native_app_glue'
DEBUG: /data/sandcastle/boxes/fbsource/tools/build_defs/fbcode_macros/build_defs/lib/cpp_common.bzl:287:14: Using disallowed linker flag 'arvr/third-party/toolchains/platform009/build/mesa/lib/libGL.so' in library rule 'fbsource//third-party/toolchains:opengl'
DEBUG: /data/sandcastle/boxes/fbsource/tools/build_defs/fbcode_macros/build_defs/lib/cpp_common.bzl:287:14: Using disallowed linker flag 'arvr/third-party/freeglut/3.0.0/libs/x64-linux/libglut.a' in library rule 'fbsource//third-party/toolchains:GLUT'
Parsing buck files: finished in 26.8 sec
Creating action graph: finished in 59.3 sec
[RE] Metadata: Session ID=[https://fburl.com/b/reSessionID-2ba31fa4-af8e-4de8-abba-76f0f1f91e45]
[RE] Waiting on 0 remote actions. Completed 45 actions remotely, action cache hit rate: 0.00%.
Downloaded 12580/12786 artifacts, 985.44 Mbytes, 0.8% cache miss (for updated rules)
Building: finished in 01:53.8 min (100%) 30935/30935 jobs, 12722/30935 updated
Total time: 03:20.0 min
More details at https://www.internalfb.com/intern/buck/build/c3bdc062-413e-4646-9ac4-79cef0af8297
BUILD SUCCEEDED
Tpx test run coordinator for Facebook. See https://fburl.com/tpx for details.
Running with tpx session id: a7cd4116-3ee3-4db2-9018-9a7c719a4d7b
Trace available for this run at /tmp/tpx-20220420-213554.773515-a7cd4116-3ee3-4db2-9018-9a7c719a4d7b/trace.log
RemoteExecution session id: reSessionID-a7cd4116-3ee3-4db2-9018-9a7c719a4d7b-tpx
Started reporting to test run: https://www.internalfb.com/intern/testinfra/testrun/3940649774928947
✓ ListingSuccess: smart/pytorch_mobile/backport_service:handler_test : 2 tests discovered (45.162)
✓ Pass: smart/pytorch_mobile/backport_service:handler_test - test_illegal_version_exception (smart.pytorch_mobile.backport_service.handler_test.BackportServiceTest) (0.398)
✓ Pass: smart/pytorch_mobile/backport_service:handler_test - test_backport (smart.pytorch_mobile.backport_service.handler_test.BackportServiceTest) (21.871)
Summary
Pass: 2
ListingSuccess: 1
```
Reviewed By: malfet, pavithranrao, guangy10
Differential Revision: D35805700
fbshipit-source-id: d40288715ec336c06dc8a91244dd5576b0af287c
(cherry picked from commit e908737fc37901ff2cb153936e3a57074146ba3a)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75996
Nested NamedTuple is supported when loading the model. However one case is missing when exporting the model. if it's the first layer, we haven't covered the `Dict` type yet.
Before:
```
// ty is a generic type pointer and can be any type
for (const TypePtr& ty : mobile_code.types_) {
std::string type_str = get_type_str(t);
if (t is TupleType) do B
}
```
After:
```
for (const TypePtr& ty : mobile_code.types_) {
std::string type_str = get_type_str(t);
if (t is DictType) do A
else if (t is TupleType) do B
}
```
ghstack-source-id: 154292348
Test Plan:
Use the uploaded model from Everstore: `GBE5xgh6J6T0ZfsAAAhQ7n_pxB90br0LAAAP`. Get it by `clowder get GBE5xgh6J6T0ZfsAAAhQ7n_pxB90br0LAAAP namedtuple.ptl`.
```
TEST(LiteInterpreterTest, DebugDper) {
std::string path =
"/data/sandcastle/boxes/fbsource/fbcode/caffe2/test/cpp/jit/namedtuple.ptl";
// mobile::Module bc = _load_for_mobile(path);
Module jit_m = load(path);
std::string resave_path =
"/data/sandcastle/boxes/fbsource/fbcode/caffe2/test/cpp/jit/namedtuple_reave.ptl";
jit_m._save_for_mobile(resave_path);
mobile::Module bc = _load_for_mobile(resave_path);
}
```
```
buck test //caffe2/test/cpp/jit:jit -- --exact 'caffe2/test/cpp/jit:jit - LiteInterpreterTest.DebugDper'
buck test mode/opt-split-dwarf //dper3/dper3/modules/tests:id_score_list_to_id_list_test
```
Reviewed By: iseeyuan
Differential Revision: D35705480
fbshipit-source-id: b8da2e720b8ca247bb40f13b67b75b5a04709f7a
(cherry picked from commit 73bb6f9ddbefcd7e55e8660a9b55ae6b9eb9759c)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75244
Original commit changeset: d653a5af662a
Original Phabricator Diff: D35060736 (d9d34922a0)
Test Plan: Model loading test, verified that D35060736 (d9d34922a0) will cause the torch::save => torch::load failure.
Reviewed By: yinghai, jianyuh
Differential Revision: D35387009
fbshipit-source-id: 9d176992d402d57779e2af3d905b3c1538335298
(cherry picked from commit 6c8cc0d3b8a88b15e35702d70e18bbae8aa4628a)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74594
Extending `_save_for_mobile` and `_load_for_mobile` to support faltbuffer format with additional optional argument which is set to pick pickle by default.
Adding new binary target with suffix `_pickle_and_flatbuffer` to help migration.
Size test in D34909502 shows the size has regressed by ~40K but after removing pickle and comparing lite_predictors we have ~120K size measure that we will achieve when deprecating pickle and moving to flatbuffer
**BEFORE:**
```lang=mermaid
graph TD;
torch_core-->torch_mobile_deserialize;
torch_mobile_core-->torch_mobile_deserialize;
jit_module_saving-->torch_core;
jit_module_saving-->torch_mobile_core;
torch_mobile_deserialize-->caffe2_serialize;
torch_mobile_deserialize-->torch_mobile_module;
caffe2_serialize-->miniz;
flatbuffer_loader-->mobile_bytecode;
flatbuffer_serializer-->mobile_bytecode;
mobile_bytecode-->flatbuffer_2.0;
flatbuffer_loader-->torch_mobile_module;
flatbuffer_serializer-->torch_mobile_module;
```
**AFTER:**
```lang=mermaid
graph TD;
torch_core-->torch_mobile_deserialize;
torch_mobile_core-->torch_mobile_deserialize;
jit_module_saving-->torch_core;
jit_module_saving-->torch_mobile_core;
torch_mobile_deserialize-->caffe2_serialize;
torch_mobile_deserialize-->torch_mobile_module;
caffe2_serialize-->miniz;
flatbuffer_loader-->mobile_bytecode;
flatbuffer_serializer-->mobile_bytecode;
mobile_bytecode-->flatbuffer_2.0;
torch_mobile_deserialize_pickle_and_flatbuffer-->|new| flatbuffer_loader;
torch_mobile_deserialize_pickle_and_flatbuffer-->|new| torch_mobile_deserialize;
torch_mobile_core_pickle_and_flatbuffer-->|new| torch_mobile_deserialize_pickle_and_flatbuffer;
torch_core_pickle_and_flatbuffer-->|new| torch_mobile_deserialize_pickle_and_flatbuffer;
jit_module_saving_pickle_and_flatbuffer-->|new| torch_core_pickle_and_flatbuffer;
jit_module_saving_pickle_and_flatbuffer-->|new| torch_mobile_core_pickle_and_flatbuffer;
flatbuffer_serializer-->torch_mobile_module;
jit_module_saving_pickle_and_flatbuffer-->|new|jit_module_saving;
jit_module_saving_pickle_and_flatbuffer-->|new|flatbuffer_serializer;
flatbuffer_loader-->torch_mobile_module;
```
Original commit changeset: 780dfb6fd6ba
Original Phabricator Diff: D34805092 (284b2b7135)
ghstack-source-id: 152044801
(Note: this ignores all push blocking failures!)
Test Plan:
CI
```
~/fbsource/fbcode] cd ~/fbsource/fbcode/ && buck test -c fbcode.caffe2_enable_flatbuffer=1 //caffe2/test/cpp/jit:jit -- FlatbufferTest.ExtraFiles
Parsing buck files: finished in 0.9 sec
Building: finished in 5.3 sec (100%) 12992/54304 jobs, 0/54304 updated
Total time: 6.2 sec
More details at https://www.internalfb.com/intern/buck/build/2b387fff-f813-4cfa-b53f-eb2378630d4e
BUILD SUCCEEDED
Tpx test run coordinator for Facebook. See https://fburl.com/tpx for details.
Running with tpx session id: f93a84d6-e7ce-41a0-a97f-0ef3fa6d199d
Trace available for this run at /tmp/tpx-20220323-134108.766518-f93a84d6-e7ce-41a0-a97f-0ef3fa6d199d/trace.log
RemoteExecution session id: reSessionID-f93a84d6-e7ce-41a0-a97f-0ef3fa6d199d-tpx
Started reporting to test run: https://www.internalfb.com/intern/testinfra/testrun/4503599723101693
✓ ListingSuccess: caffe2/test/cpp/jit:jit : 486 tests discovered (19.122)
✓ Pass: caffe2/test/cpp/jit:jit - FlatbufferTest.ExtraFiles (0.187)
Summary
Pass: 1
ListingSuccess: 1
If you need help understanding your runs, please follow the wiki: https://fburl.com/posting_in_tpx_users
Finished test run: https://www.internalfb.com/intern/testinfra/testrun/4503599723101693
```
Similar Build Deps Dags
```
[pavithran@devvm5216.vll0 /data/users/pavithran/fbsource] buck query 'allpaths(//xplat/caffe2:torch_mobile_all_ops_pickle_and_flatbuffer, //xplat/caffe2:torch_mobile_deserialize_pickle_and_flatbuffer)' --output-format dot-compact | pastry
P486770901: https://www.internalfb.com/intern/paste/P486770901/
[pavithran@devvm5216.vll0 /data/users/pavithran/fbsource] buck query 'allpaths(//xplat/caffe2:torch_mobile_all_ops, //xplat/caffe2:torch_mobile_deserialize)' --output-format dot-compact | pastry
P486771278: https://www.internalfb.com/intern/paste/P486771278/
```
pickle_and_flatbuffer: https://www.internalfb.com/intern/dgw/graph/?build_id=P486770901
pickle: https://www.internalfb.com/intern/dgw/graph/?build_id=P486771278
Reviewed By: iseeyuan
Differential Revision: D35067157
fbshipit-source-id: 9044259c17a2e0da79bd6aedb28efbdfd57e23e0
(cherry picked from commit f738069ec3a72e79da56172741d027de514e9e5f)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73435
Add support for torch.jit.save and load for meta tensors to use in meta tensor based xl weights.
Test Plan:
```
buck test //caffe2/test:jit && -- -r .*save_load_meta_tensors.*
```
Reviewed By: houseroad
Differential Revision: D34479511
fbshipit-source-id: 117ccb12e9e427290a17297204508ec85495e3be
(cherry picked from commit ee9aaaf8208d6c9530c828a4b9f28cf2cca05630)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/71662
backport v8 to v7 to support promoted ops as instruction
a flag to help export as instruction from v8 and export as operators for v7 and below
Test Plan:
```
buck test caffe2/test/cpp/jit:jit -- LiteInterpreterTest.BackPortByteCodeModelAllVersions
Started reporting to test run: https://www.internalfb.com/intern/testinfra/testrun/5629499620570927
✓ ListingSuccess: caffe2/test/cpp/jit:jit : 461 tests discovered (15.693)
✓ Pass: caffe2/test/cpp/jit:jit - LiteInterpreterTest.BackPortByteCodeModelAllVersions (2.712)
Summary
Pass: 1
ListingSuccess: 1
If you need help understanding your runs, please follow the wiki: https://fburl.com/posting_in_tpx_users
Finished test run: https://www.internalfb.com/intern/testinfra/testrun/5629499620570927
```
```
buck run mode/opt //caffe2/torch/fb/mobile/upgrader_codegen:upgrader_codegen
buck test mode/opt //caffe2/test:upgrader_codegen -- mobile.test_upgrader_codegen.TestLiteScriptModule
Parsing buck files: finished in 0.8 sec
Downloaded 0/2 artifacts, 0.00 bytes, 100.0% cache miss (for updated rules)
Building: finished in 01:39.4 min (100%) 11031/11031 jobs, 2/11031 updated
Total time: 01:40.2 min
More details at https://www.internalfb.com/intern/buck/build/a8b0e417-019c-44ba-be6b-23379411a965
BUILD SUCCEEDED
Tpx test run coordinator for Facebook. See https://fburl.com/tpx for details.
Running with tpx session id: 44fbfa66-cce8-4277-82ac-f89d79558581
Trace available for this run at /tmp/tpx-20220202-160956.915412/trace.log
RemoteExecution session id: reSessionID-44fbfa66-cce8-4277-82ac-f89d79558581-tpx
Started reporting to test run: https://www.internalfb.com/intern/testinfra/testrun/281475200877601
✓ ListingSuccess: caffe2/test:upgrader_codegen : 1 tests discovered (1.249)
✓ Pass: caffe2/test:upgrader_codegen - test_generate_bytecode (mobile.test_upgrader_codegen.TestLiteScriptModule) (1.365)
Summary
Pass: 1
ListingSuccess: 1
If you need help understanding your runs, please follow the wiki: https://fburl.com/posting_in_tpx_users
Finished test run: https://www.internalfb.com/intern/testinfra/testrun/281475200877601
```
Reviewed By: iseeyuan
Differential Revision: D33719098
fbshipit-source-id: e2d2b23d298f98e4d4fcdfc344f7b8c6f92cff26
(cherry picked from commit 81b956c23abc19489b69eee986721252474d00dc)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/71968
Right now when we output type to python files under `code/`, we directly write the dynamic type representation `Dynamic<>`, which causes server side to load an unsupported type. Instead we should do the fallback in export_module.cpp.
ghstack-source-id: 147856473
Test Plan:
CI
buck test //xplat/pytorch/mobile/test:test_read_all_mobile_model_configs
```
...
[ OK ] GeneralAndSpecial/BackPortTest.BackPortForChunkIdx/37 (39142 ms)
[ RUN ] GeneralAndSpecial/BackPortTest.BackPortForChunkIdx/38
total: 6 success: 6 failure: 0
[ OK ] GeneralAndSpecial/BackPortTest.BackPortForChunkIdx/38 (9651 ms)
[ RUN ] GeneralAndSpecial/BackPortTest.BackPortForChunkIdx/39
total: 4 success: 4 failure: 0
[ OK ] GeneralAndSpecial/BackPortTest.BackPortForChunkIdx/39 (5509 ms)
[----------] 40 tests from GeneralAndSpecial/BackPortTest (806244 ms total)
[----------] Global test environment tear-down
[==========] 41 tests from 2 test cases ran. (810453 ms total)
[ PASSED ] 41 tests.
```
Reviewed By: pavithranrao
Differential Revision: D33830355
fbshipit-source-id: 0be608fadf14daa2b703f31118ab648cb7b75f9b
(cherry picked from commit 6d65049ae5ac1ef6a11d19de48dd4d926b793b34)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/71922
Use proper name in the error message and remove "torchbind", since it's not official in documentation.
Test Plan: Imported from OSS
Reviewed By: cccclai
Differential Revision: D33824899
Pulled By: iseeyuan
fbshipit-source-id: 41968494c04fab39292d9cc4dc6e15cca99cbff4
(cherry picked from commit 9732a52ed264f013e9ba3844f86be11d31444954)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/68037
Right now mobile::Code doesn't outlive its enclosing Function, and all accesses to Code happens inside interpreter loop which doesn't outlive the module, so we don't need to use std::shared_ptr here. This also should saves us 1-2 KB for binary size, because shared_ptr seems to bloat on arm64 android.
ghstack-source-id: 145818696
Test Plan: eyes.
Reviewed By: qihqi, tugsbayasgalan
Differential Revision: D32264616
fbshipit-source-id: d83f538d6604cf75fd7728a25127b4849ce7ab2a
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/69412
TypePrinter does not need to take ownership of the Type.
This helps unblock the following diff to stop refcounting Type singletons.
ghstack-source-id: 145671619
Test Plan: CI
Reviewed By: suo
Differential Revision: D32858525
fbshipit-source-id: df58676938fd20c7bae4a366d70b2067a852282d
Summary:
1. is to convert Function -> mobile::Function
2. is to serialize mobile::Function
This also opens opportunity to create mobile::Module without saving/reloading
Fixes #{issue number}
Pull Request resolved: https://github.com/pytorch/pytorch/pull/66494
Reviewed By: zhxchen17
Differential Revision: D32293022
Pulled By: qihqi
fbshipit-source-id: 29b43d47ff86071d5e2f9d6ca4dba4445711ce3d
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/67750
Add more information about why exporting model fails.
Before: error message:
```
E1102 22:57:42.984015 3220949 ExceptionTracer.cpp:221] exception stack complete
terminate called after throwing an instance of 'c10::Error'
what(): __torch__ types other than torchbind (__torch__.torch.classes)are not supported in lite interpreter. Workaround: instead of using arbitrary class type (class Foo()), define a pytorch class (class Foo(torch.nn.Module)). The problematic type is: __torch__.dper3.core.schema_utils.IdListFeature
Exception raised from getFunctionTuple at caffe2/torch/csrc/jit/serialization/export_module.cpp:246 (most recent call first):
```
After
```
E1102 22:57:42.984015 3220949 ExceptionTracer.cpp:221] exception stack complete
terminate called after throwing an instance of 'c10::Error'
what(): __torch__ types other than torchbind (__torch__.torch.classes)are not supported in lite interpreter. Workaround: instead of using arbitrary class type (class Foo()), define a pytorch class (class Foo(torch.nn.Module)).
Exception raised from getFunctionTuple at caffe2/torch/csrc/jit/serialization/export_module.cpp:246 (most recent call first):
```
ghstack-source-id: 143009294
Test Plan: CI
Reviewed By: larryliu0820
Differential Revision: D32129397
fbshipit-source-id: 0594a98a59f727dc284acd1c9bebcd7589ee7cbb
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/65381
The previous diff adds a way to make Tuples of size 3 or less
more efficiently. This diff makes it easier to hit that path and
updates a bunch of callsites to hit it.
ghstack-source-id: 142065832
Test Plan: CI
Reviewed By: ezyang
Differential Revision: D31069538
fbshipit-source-id: d04da3709594ed68ab1c0a1471f8cffd8d001628
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/65967
Graph is an implementation detail. If user wants to get access to the
underlying graph, they should be able to explicitly dynamic cast instead.
ghstack-source-id: 141659819
Test Plan: no behavior change.
Reviewed By: gmagogsfm
Differential Revision: D31326153
fbshipit-source-id: a0e984f57c6013494b92a7095bf5bb660035eb84
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/65966
ghstack-source-id: 141594521
Support exportation of "interface methods" from submodule to a mobile module. "Interface methods" are defined as methods which might be dynamically called in a module therefore need to be exported anyway, like virtual functions in C++.
Before this change the algorithm of exportation is a simple iteration through all toplevel methods. Now since we have indirect calls, we need to recursively walkthrough the call graph to find all potentially used methods, which means the order we export methods might break in old runtimes, to guarantee forward compatibility we need to export toplevel methods first, then extra methods, in this order toplevel methods will always be found first.
NOTE that interface methods exportations are disabled by default in this diff. We need to call torch._C._enable_mobile_interface_call_export to actaully enable it.
Test Plan: buck test mode/dev //caffe2/test:jit -- --exact 'caffe2/test:jit - test_export_opnames_interface (jit.test_misc.TestMisc)'
Reviewed By: qihqi, iseeyuan
Differential Revision: D31326155
fbshipit-source-id: 5be7234cca07691f62648a85133b6db65e427b53
Summary:
Add type support for namedtule custom class. For the namedtuple type, it will deserailize to the following format in string
```
"qualified_named[
NamedTuple, [
[filed_name_1, field_type_1],
[filed_name_2, field_type_2]
]
]"
```
If it's nested, it will be
```
"__torch__.A[
NamedTuple, [
[field_name_a, __torch__.B [
NamedTuple, [
[field_name_b, __torch__.C [
NamedTuple, [
[field_name_c_1, Tensor],
[field_name_c_2, Tuple[Tensor, Tensor]],
]
]
]
]
]
]
]
]
"
```
The nametuple type includes both `collection` and `typing`.
```
from typing import NamedTuple
from collections import namedtuple
```
It will be a forward incompatible change. However this type is never supported and exported before and we don't have a proper way to backport it. The optimum solution to ship this change is probably
1. Update the change for import without the change to export. So the runtime can read the new format, but no new format will be exported.
2. Update the change to export the new type. So runtime can export new format.
For the following example:
```
class Foo(NamedTuple):
id: torch.Tensor
class Bar(torch.nn.Module):
def __init__(self):
super(Bar, self).__init__()
self.foo = Foo(torch.tensor(1))
def forward(self, a: torch.Tensor):
self.foo = Foo(a)
return self.foo
```
The new bytecode.pkl will be
```
(6,
('__torch__.mobile.test_lite_script_type.MyTestModule.forward',
(('instructions',
(('STOREN', 1, 2),
('DROPR', 1, 0),
('MOVE', 2, 0),
('LIST_CONSTRUCT', 0, 1),
('NAMED_TUPLE_CONSTRUCT', 1, 1),
('RET', 0, 0))),
('operators', ()),
('constants', ()),
('types',
('List[Tensor]',
'__torch__.mobile.test_lite_script_type.myNamedTuple[NamedTuple, [[a, '
'List[Tensor]]]]')),
('register_size', 2)),
(('arguments',
((('name', 'self'),
('type', '__torch__.mobile.test_lite_script_type.MyTestModule'),
('default_value', None)),
(('name', 'a'), ('type', 'Tensor'), ('default_value', None)))),
('returns',
((('name', ''),
('type', '__torch__.mobile.test_lite_script_type.myNamedTuple'),
('default_value', None)),)))))
```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/62612
ghstack-source-id: 141485500
Test Plan:
fb:
1. Add a simple unittest to test NamedTuple custom class
2. Use following cpp code (D30271153)
```
TEST(LiteTrainerTest, CustomOp) {
std::string jit_model =
"/home/chenlai/local/notebooks/ads_dper_fl_model_282250609.pt";
Module jit_m = load(jit_model);
jit_m.eval();
torch::jit::Module module_freeze = freeze(jit_m);
IValue tuple =
c10::ivalue::Tuple::create({1 * torch::ones({10, 1034}), 3 * torch::ones({10, 1034})});
std::vector<IValue> inputs_1{tuple};
auto jit_output = jit_m.forward(inputs_1);
jit_output.dump();
std::stringstream ss;
jit_m._save_for_mobile(ss);
jit_m._save_for_mobile("/home/chenlai/local/notebooks/tmp/tmp.ptl");
torch::jit::mobile::Module mobile_m = _load_for_mobile(ss);
auto mobile_output = mobile_m.forward(inputs_1);
std::cout << "mobile output: " << std::endl;
mobile_output.dump();
}
```
And output from both mobile and jit are
```
{prediction: ([ CPUFloatType{0} ], [ CPUFloatType{0} ])}
```
3. N1033894 with model inspection, also compare the result between jit and mobile with the dper model.
Reviewed By: iseeyuan
Differential Revision: D30004716
fbshipit-source-id: cfd30955e66a604af8f9633b1b608feddc13d7d7
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64065
It is only safe to mutate Tuple elements if you are the sole owner
of the tuple. The most efficient way to do this, then, is
`std::move(*std::move(tupleIValue).toTuple()).elements()` (the
innermost move allows `IValue::toTuple()` to avoid a refcount bump and
the outermost move allows the element vector to be moved out of the
tuple), but many callsites write simply
`tupleIValue.toTuple().elements()`, which incurs many extra refcount
bumps.
ghstack-source-id: 139468088
Test Plan: CI
Reviewed By: ezyang
Differential Revision: D30592621
fbshipit-source-id: e8312de866de09b9ea2a62e5128cbf403ee16f09
Summary:
1. Enable support for operators with default args and out args. For `torch.add(x, h, out=x)`, the number of specified arguments will be 3 instead of 4.
2. Bump bytecode version from 6 to 7
3. Implement backport_v7_to_v6 function. Also slightly refactor the local_thread to allow re-emit operators.
4. unittest to cover backport function
5. Update expect result from 4 to 3 in unit test DefaultArgsWithOutArg to cover the number of specified arguments.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/63651
ghstack-source-id: 138539912
Test Plan:
```
caffe2/test/cpp/jit:jit - LiteInterpreterTest.DefaultArgsWithOutArg
caffe2/test/cpp/jit:jit - LiteInterpreterTest.DefaultArgsPinvWithOutArg
caffe2/test/cpp/jit:jit - LiteInterpreterTest.BackPortByteCodeModelAllVersions
```
Reviewed By: raziel, tugsbayasgalan
Differential Revision: D30454080
fbshipit-source-id: 357c50b96682430675142d20d688d1f64e1de307
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64268
If the same pair of operator name and num inputs have been used to add an instruction to the operator table previously (and the operator's schema is not vararg), use the same index as that instruction rather than creating a new one.
ghstack-source-id: 138014905
Test Plan: Phabricator tests, and test performance changes in next diff
Reviewed By: iseeyuan, tugsbayasgalan
Differential Revision: D30615434
fbshipit-source-id: f442f557f12412693a73004ce44733ccef063b82
