Summary: Move storage saving to last step, because otherwise tensors saved after storage are already saved will not have storage.
Test Plan: Tested by loading the file in `clowder get GLDGLQnKrIsQFg8DAPxq9vg59ZwZbmQwAAAA orig.pt` and converting to flatbuffer and load again
Differential Revision: D36552645
Pull Request resolved: https://github.com/pytorch/pytorch/pull/78024
Approved by: https://github.com/Jack-Khuu
This makes prims look as if they were defined in native_functions.yaml
but they're still all written in Python. You now need to give a full
schema string for your prims. The returned prim object is now
torch.ops.prim overload (prims are not allowed to be overloaded,
so we return the overload, not the overload packet, for speed.)
Signed-off-by: Edward Z. Yang <ezyangfb.com>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/77117
Approved by: https://github.com/mruberry, https://github.com/albanD
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73284
Some important ops won't support optional type until opset 16,
so we can't fully test things end-to-end, but I believe this should
be all that's needed. Once ONNX Runtime supports opset 16,
we can do more testing and fix any remaining bugs.
Test Plan: Imported from OSS
Reviewed By: albanD
Differential Revision: D34625646
Pulled By: malfet
fbshipit-source-id: 537fcbc1e9d87686cc61f5bd66a997e99cec287b
Co-authored-by: BowenBao <bowbao@microsoft.com>
Co-authored-by: neginraoof <neginmr@utexas.edu>
Co-authored-by: Nikita Shulga <nshulga@fb.com>
(cherry picked from commit 822e79f31ae54d73407f34f166b654f4ba115ea5)
Summary:
This enables previous change made at D35196883 (b34b192d6b)
Previous change is landed for 2 weeks to make sure that the format change introduced here will be handed in code.
Test Plan: existing tests
Differential Revision: D36074453
Pull Request resolved: https://github.com/pytorch/pytorch/pull/76688
Approved by: https://github.com/gmagogsfm
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/76197
some class only have setstate but not getstate. Those should be able to serialize correctly.
Test Plan:
by hand
`buck run fbcode/mode/dbg xplat/caffe2/fb/lite_predictor:convert_model -- --model=$HOME/models/pytorchmodel_from_manifold.pt --output_name=$HOME/models/pytorchmodel.ff --use_original_bytecode=1`
the model above is a .pt file created using version 4 of bytecode. In particular, __setstate__ is serialized there but __getstate__ is not.
Reviewed By: pavithranrao
Differential Revision: D35827479
fbshipit-source-id: 3d3fdb63d20d41170eac46d076b162d213169f96
(cherry picked from commit 13e966e5c62ce3faf85e8f8fe20e50ad9bb240e5)
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/76187
The file `torch/csrc/jit/serialization/mobile_bytecode_generated.h` should be a generated file not edited by hand anymore. for internal usage please use `caffe2:mobile_byecode`. For OSS, until it is generated on thee fly, this checked in file will be used.
ghstack-source-id: 154485024
(Note: this ignores all push blocking failures!)
Test Plan: CI
Reviewed By: qihqi
Differential Revision: D35822915
fbshipit-source-id: d64e2a270f58c82cccafdd9139e080af923b314d
(cherry picked from commit 80ee9f4bdd6cf371abcb1551889c5c2068942942)
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:
## Original commit message:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73368
debug_pkl file inside of pytorch's .pt file consists of a list of SourceRanges. Each SourceRange points to a Source which is a stack track, filename, and start, end numbers. Those are emitted in debug_pkl file as strings.
Since many SourceRange shares the same source, the string for trace can be deduped.
The newer format saves a set of unique traces in a tuple, then each SourceRange will save the offset of it's trace w.r.t. position in that tuple. (i.e. manually applying dictionary compression).
The above helps with smaller file size. On loading, if we copy each trace to Source as string the runtime memory would still blowup.
To mitigate this, we use SourceView directly instead of source which will take the reference of string inside of Deserializer and make that into string_view. This is safe because Deserializer is hold by Unpickler by shared_ptr, and Unpickler is also hold by shared_ptr by another Source object. That Source object will be alive during the model construction.
Test Plan:
## Original Test plan
unit test
Took original file (312271638_930.predictor.disagg.local); loaded with `torch.jit.load` save again with `torch.jit.save`. Unzip both, look at contents:
```
[qihan@devvm5585.vll0 ~]$ du archive -h
4.0K archive/xl_model_weights
3.7M archive/extra
8.0K archive/code/__torch__/caffe2/torch/fb/model_transform/splitting
8.0K archive/code/__torch__/caffe2/torch/fb/model_transform
8.0K archive/code/__torch__/caffe2/torch/fb
8.0K archive/code/__torch__/caffe2/torch
8.0K archive/code/__torch__/caffe2
20M archive/code/__torch__/torch/fx/graph_module
20M archive/code/__torch__/torch/fx
8.0K archive/code/__torch__/torch/classes
20M archive/code/__torch__/torch
20M archive/code/__torch__
20M archive/code
2.7M archive/constants
35M archive
[qihan@devvm5585.vll0 ~]$ du resaved -h
4.0K resaved/extra
8.0K resaved/code/__torch__/caffe2/torch/fb/model_transform/splitting
8.0K resaved/code/__torch__/caffe2/torch/fb/model_transform
8.0K resaved/code/__torch__/caffe2/torch/fb
8.0K resaved/code/__torch__/caffe2/torch
8.0K resaved/code/__torch__/caffe2
1.3M resaved/code/__torch__/torch/fx/graph_module
1.3M resaved/code/__torch__/torch/fx
8.0K resaved/code/__torch__/torch/classes
1.4M resaved/code/__torch__/torch
1.4M resaved/code/__torch__
1.4M resaved/code
2.7M resaved/constants
13M resaved
[qihan@devvm5585.vll0 ~]$
```
## Additional test:
`buck test mode/dev-tsan //caffe2/benchmarks/static_runtime:static_runtime_cpptest -- --exact 'caffe2/benchmarks/static_runtime:static_runtime_cpptest - StaticRuntime.to'` passes
test jest.fbios.startup_cold_start.local.simulator f333356873 -
Differential Revision: D35196883
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74869
Approved by: https://github.com/gmagogsfm
This PR introduces 3 BC changes:
First, this PR propagates `BUILD_CAFFE2` flag to `libtorch` and `libtorch_python`, which is necessary for non-caffe2 ONNX runtimes when using `ONNX_ATEN_FALLBACK` operator export type.
Second, as a complement of https://github.com/pytorch/pytorch/pull/68490, this PR refactors Caffe2's Aten ops symbolics to consider not only the `operator_export_type` (aka `ONNX_ATEN_FALLBACK`) to emit Caffe2 Aten ops, but also whether `BUILD_CAFFE2` (which is called `torch.onnx._CAFFE2_ATEN_FALLBACK` in python binding) is set.
Lastly, it renames `onnx::ATen` to `aten::ATen` for ONNX spec consistency in a BC fashion.
ONNX doesn't have `ATen` op on its spec, but PyTorch ONNX converter emits them. Non-Caffe2 backend engines would be mislead by such operator's name/domain. A non-ideal workaround would be to have Aten ops handled based on its name and ignore the (non-complaint) domain. Moreover, users could incorrectly file bugs to either ONNX or ONNX Runtime when they inspect the model and notice the presence of an unspecified ONNX operator.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73954
Approved by: https://github.com/BowenBao, https://github.com/malfet, https://github.com/garymm, https://github.com/jiafatom
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75201
In this diff:
1. Bump supported version to 9, which will serve as a placeholder for upcoming version bump to v9 for flatbuffer format migration.
2. Implements backport from v9 flatbuffer file to v8 pickle file.
ghstack-source-id: 153225189
(Note: this ignores all push blocking failures!)
Test Plan:
fb:
```
cd ~/fbsource/fbcode/ && buck test -c fbcode.caffe2_enable_flatbuffer=1 caffe2/test/cpp/jit:jit -- LiteInterpreterTest.BackPortByteCodeModelAllVersions
Parsing buck files: finished in 0.7 sec
Downloaded 0/25 artifacts, 0.00 bytes, 100.0% cache miss (for updated rules)
Building: finished in 20.7 sec (100%) 21783/21783 jobs, 5/21783 updated
cd ~/fbsource/fbcode/ && buck test caffe2/test/cpp/jit:jit -- FlatbufferTest.FlatbufferBackPortTest
Parsing buck files: finished in 0.7 sec
Building: finished in 4.5 sec (100%) 12972/53298 jobs, 0/53298 updated
Total time: 5.3 sec
More details at https://www.internalfb.com/intern/buck/build/b658d597-d358-4293-97cb-28e7612b96e8
BUILD SUCCEEDED
Tpx test run coordinator for Facebook. See https://fburl.com/tpx for details.
Running with tpx session id: 35d5542d-6ee3-4c28-be10-1d822c7a6fef
Trace available for this run at /tmp/tpx-20220308-090347.891303-35d5542d-6ee3-4c28-be10-1d822c7a6fef/trace.log
RemoteExecution session id: reSessionID-35d5542d-6ee3-4c28-be10-1d822c7a6fef-tpx
Started reporting to test run: https://www.internalfb.com/intern/testinfra/testrun/8444249379196000
✓ ListingSuccess: caffe2/test/cpp/jit:jit : 490 tests discovered (22.838)
✓ Pass: caffe2/test/cpp/jit:jit - FlatbufferTest.FlatbufferBackPortTest (0.289)
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/8444249379196000
```
Reviewed By: iseeyuan
Differential Revision: D34702597
fbshipit-source-id: 5c203c29d13360d7934ce6e57557739e7038c05e
(cherry picked from commit 6189e08a2bd968fdab636f77cb6bd73d6c36beb2)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/57775
The minimum supported bytecode version is updated from 3 to 4. We no longer support version 3 bytecode models.
Why?
* There are hacky codes in operator loading, that performs differently on one operator on the global bytecode version 3. Instead operator related metadata should be passed (for example, in #56845). To allow future development, we remove the hacky way first.
* The bytecode version was bumped from 3 to 4 more than half a year ago. Since all the production models are all bumped to version 4, it's not practical to keep and maintain version 3. The risk to deprecate version 3 is low.
Test Plan: Imported from OSS
Reviewed By: raziel
Differential Revision: D28270791
Pulled By: cccclai
fbshipit-source-id: 70b1bd6352fdaae5f8d2173b81578d77018c8e44
(cherry picked from commit 3e930fa381cd01f3705116795c6426df992372fc)
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:
This PR introduces `SymInt` type to Pytorch which will be used by LTC and AOTAutograd for tracing size arithmetic and tests.
`SymInt` is a C++ union structure [int64_t, SymbolicIntNode*] that wraps around an int64_t field where the value of the field could be an index into a list of `shared_ptr<SymbolicIntNode>` or a real int.
This PR doesn't add any support for actually tracing symbolic ints. i.e. data_ for now can only contain real ints.
```
Goal 1: just to show we can add a type to PyTorch core. (wraps int) LANDEABLE
Finalize the naming - symint
Want the name to be short
Does invoke “size” - NO
SInt/SymInt/SymbolicInt
SInt could mean signed int
sym_int or symint or SymInt (originally it was “int”; capitalized implies object semantics, whereas lowercase implies value semantics)
JIT schema - symint
C++ - symint
```
See more details here: https://docs.google.com/document/d/1iiLNwR5ohAsw_ymfnOpDsyF6L9RTUaHMpD8 (d843f63f2a)YLw-jxEw
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74861
Reviewed By: qihqi, ngimel
Differential Revision: D35226230
Pulled By: Krovatkin
fbshipit-source-id: 34acf342bd50fcaa4d8d5dd49c2fd6a98823a5b3
(cherry picked from commit 218643f63ef181cabb92d13a6e837eb64f2dda3c)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74989
Adding bytecode and operator version to be serialized in flatbuffer files
ghstack-source-id: 152720235
(Note: this ignores all push blocking failures!)
Test Plan: CI
Reviewed By: iseeyuan
Differential Revision: D35265693
fbshipit-source-id: f47a21036e82c0df3e787e3f330a8140f9c922fc
(cherry picked from commit fc1d9b8dadaf454109a5c9ae583f283b2550ee4e)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74387
Make temporary python bindings for flatbuffer to test ScriptModule save / load.
(Note: this ignores all push blocking failures!)
Test Plan: unittest
Reviewed By: iseeyuan
Differential Revision: D34968080
fbshipit-source-id: d23b16abda6e4b7ecf6b1198ed6e00908a3db903
(cherry picked from commit 5cbbc390c5f54146a1c469106ab4a6286c754325)
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:
Add ONNX exporter logging facility. Supporting both C++/Python logging api. Logging can be turned on/off. Logging output stream can be either set to `stdout` or `stderr`.
A few other changes:
* When exception is raised in passes, the current IR graph being processed will be logged.
* When exception is raised from `_jit_pass_onnx` (the pass that converts nodes from namespace `ATen` to `ONNX`), both ATen IR graph and ONNX IR graph under construction will be logged.
* Exception message for ConstantFolding is truncated to avoid being too verbose.
* Update the final printed IR graph with node name in ONNX ModelProto as node attribute. Torch IR Node does not have name. Adding this to printed IR graph helps debugging.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/71342
Reviewed By: msaroufim
Differential Revision: D34433473
Pulled By: malfet
fbshipit-source-id: 4b137dfd6a33eb681a5f2612f19aadf5dfe3d84a
(cherry picked from commit 67a8ebed5192c266f604bdcca931df6fe589699f)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74119
implemented function to generate source as ExtraFilesMap and constants
wrote function to construct jit module given (ivalue, source,
constant) tripple.
Test Plan: unittest
Reviewed By: pavithranrao
Differential Revision: D34803945
fbshipit-source-id: 2edc798407fe68294cb4c3c7516f5bd143df88c3
(cherry picked from commit 35e54e166b8f0f5cfe8f08c07866b59ae61ee79d)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74084
Now that the schema includes a magic file header string, write it to the flatbuffer data generated by `flatbuffer_serializer`.
ghstack-source-id: 151109277
Test Plan: A later diff in this stack (D34408538) tests that the output data contains the magic header.
Reviewed By: pavithranrao
Differential Revision: D34809318
fbshipit-source-id: edb45d57e56fa4b30675eb9ce6e4e258abfd5417
(cherry picked from commit f5e8a3ff70eba186ac9e7b91739010e55cd6c5a6)
Summary:
Update flatbuffer generated header and add it to ignore for clang format
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73810
Test Plan: CI
Reviewed By: iseeyuan
Differential Revision: D34652217
Pulled By: qihqi
fbshipit-source-id: fe281afd25d618d2e4852d6b76b813e2fbee0ddc
(cherry picked from commit 095ee360b573506ac946de142bd266b8d3bac58e)
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:
This diff is reverting D34455360 (61d6c43864)
D34455360 (61d6c43864) is making the following tests to fail and this revert diff is either the revert of the blame diff or the revert of the stack of diffs that need to be reverted to revert the blame diff
Tests affected:
- https://www.internalfb.com/intern/test/562950004334605/
Multisect link:
https://www.internalfb.com/intern/testinfra/multisect/756170
Test Plan: NA
Reviewed By: zhxchen17
Differential Revision: D34596156
fbshipit-source-id: a465bca0094db3caf6130c80f1ed49eea981359b
(cherry picked from commit ef5e5578c64ce9827570757fb016aafa9c782c6a)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73368
debug_pkl file inside of pytorch's .pt file consists of a list of SourceRanges. Each SourceRange points to a Source which is a stack track, filename, and start, end numbers. Those are emitted in debug_pkl file as strings.
Since many SourceRange shares the same source, the string for trace can be deduped.
The newer format saves a set of unique traces in a tuple, then each SourceRange will save the offset of it's trace w.r.t. position in that tuple. (i.e. manually applying dictionary compression).
The above helps with smaller file size. On loading, if we copy each trace to Source as string the runtime memory would still blowup.
To mitigate this, we use SourceView directly instead of source which will take the reference of string inside of Deserializer and make that into string_view. This is safe because Deserializer is hold by Unpickler by shared_ptr, and Unpickler is also hold by shared_ptr by another Source object. That Source object will be alive during the model construction.
Test Plan:
unit test
Took original file (312271638_930.predictor.disagg.local); loaded with `torch.jit.load` save again with `torch.jit.save`. Unzip both, look at contents:
```
[qihan@devvm5585.vll0 ~]$ du archive -h
4.0K archive/xl_model_weights
3.7M archive/extra
8.0K archive/code/__torch__/caffe2/torch/fb/model_transform/splitting
8.0K archive/code/__torch__/caffe2/torch/fb/model_transform
8.0K archive/code/__torch__/caffe2/torch/fb
8.0K archive/code/__torch__/caffe2/torch
8.0K archive/code/__torch__/caffe2
20M archive/code/__torch__/torch/fx/graph_module
20M archive/code/__torch__/torch/fx
8.0K archive/code/__torch__/torch/classes
20M archive/code/__torch__/torch
20M archive/code/__torch__
20M archive/code
2.7M archive/constants
35M archive
[qihan@devvm5585.vll0 ~]$ du resaved -h
4.0K resaved/extra
8.0K resaved/code/__torch__/caffe2/torch/fb/model_transform/splitting
8.0K resaved/code/__torch__/caffe2/torch/fb/model_transform
8.0K resaved/code/__torch__/caffe2/torch/fb
8.0K resaved/code/__torch__/caffe2/torch
8.0K resaved/code/__torch__/caffe2
1.3M resaved/code/__torch__/torch/fx/graph_module
1.3M resaved/code/__torch__/torch/fx
8.0K resaved/code/__torch__/torch/classes
1.4M resaved/code/__torch__/torch
1.4M resaved/code/__torch__
1.4M resaved/code
2.7M resaved/constants
13M resaved
[qihan@devvm5585.vll0 ~]$
```
Reviewed By: gmagogsfm
Differential Revision: D34455360
fbshipit-source-id: 8cc716f9bba7183746b1b4ecc33a2de34ac503b9
(cherry picked from commit f1a04730fc9ac8fdab6c8e4c44cb5529e42090e4)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/72951
Extend flatbuffer to support extra files map
Flatbuffer schema has extra files. The users can write extra files by providing a `map<string, string>` which will be part of the flatbuffer model asset and and can be loaded back similar to pickle.
ghstack-source-id: 149622799
Test Plan:
fb:
```[pavithran@devvm5216.vll0 ~/fbsource/fbcode] cd ~/fbsource/fbcode/ && buck test caffe2/test/cpp/jit:jit -- FlatbufferTest.ExtraFiles
Parsing buck files: finished in 0.7 sec
Downloaded 0/8 artifacts, 0.00 bytes, 100.0% cache miss (for updated rules)
Building: finished in 20.0 sec (100%) 22343/22343 jobs, 4/22343 updated
Total time: 20.7 sec
More details at https://www.internalfb.com/intern/buck/build/7dba5034-d623-4a1e-afa1-b0e809df7066
BUILD SUCCEEDED
Tpx test run coordinator for Facebook. See https://fburl.com/tpx for details.
Running with tpx session id: 9c1ac1e0-a8c0-4a62-95df-8f49695aa7d1
Trace available for this run at /tmp/tpx-20220216-144630.207992/trace.log
RemoteExecution session id: reSessionID-9c1ac1e0-a8c0-4a62-95df-8f49695aa7d1-tpx
Started reporting to test run: https://www.internalfb.com/intern/testinfra/testrun/7318349470518809
✓ ListingSuccess: caffe2/test/cpp/jit:jit : 468 tests discovered (17.211)
✓ Pass: caffe2/test/cpp/jit:jit - FlatbufferTest.ExtraFiles (0.169)
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/7318349470518809````
Reviewed By: iseeyuan
Differential Revision: D34286346
fbshipit-source-id: 4e09ab25b8ed6af6f8923db3aab046c255f13bb8
(cherry picked from commit ce8d88e22a360b25253d8a75f428d523fa88a79a)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/72596
debug_pkl file inside of pytorch's .pt file consists of a list of SourceRanges. Each SourceRange points to a Source which is a stack track, filename, and start, end numbers. Those are emitted in debug_pkl file as strings.
Since many SourceRange shares the same source, the string for trace can be deduped.
The newer format saves a set of unique traces in a tuple, then each SourceRange will save the offset of it's trace w.r.t. position in that tuple. (i.e. manually applying dictionary compression).
The above helps with smaller file size. On loading, if we copy each trace to Source as string the runtime memory would still blowup.
To mitigate this, we use SourceView directly instead of source which will take the reference of string inside of Deserializer and make that into string_view. This is safe because Deserializer is hold by Unpickler by shared_ptr, and Unpickler is also hold by shared_ptr by another Source object. That Source object will be alive during the model construction.
Test Plan:
unit test
Took original file (312271638_930.predictor.disagg.local); loaded with `torch.jit.load` save again with `torch.jit.save`. Unzip both, look at contents:
```
[qihan@devvm5585.vll0 ~]$ du archive -h
4.0K archive/xl_model_weights
3.7M archive/extra
8.0K archive/code/__torch__/caffe2/torch/fb/model_transform/splitting
8.0K archive/code/__torch__/caffe2/torch/fb/model_transform
8.0K archive/code/__torch__/caffe2/torch/fb
8.0K archive/code/__torch__/caffe2/torch
8.0K archive/code/__torch__/caffe2
20M archive/code/__torch__/torch/fx/graph_module
20M archive/code/__torch__/torch/fx
8.0K archive/code/__torch__/torch/classes
20M archive/code/__torch__/torch
20M archive/code/__torch__
20M archive/code
2.7M archive/constants
35M archive
[qihan@devvm5585.vll0 ~]$ du resaved -h
4.0K resaved/extra
8.0K resaved/code/__torch__/caffe2/torch/fb/model_transform/splitting
8.0K resaved/code/__torch__/caffe2/torch/fb/model_transform
8.0K resaved/code/__torch__/caffe2/torch/fb
8.0K resaved/code/__torch__/caffe2/torch
8.0K resaved/code/__torch__/caffe2
1.3M resaved/code/__torch__/torch/fx/graph_module
1.3M resaved/code/__torch__/torch/fx
8.0K resaved/code/__torch__/torch/classes
1.4M resaved/code/__torch__/torch
1.4M resaved/code/__torch__
1.4M resaved/code
2.7M resaved/constants
13M resaved
[qihan@devvm5585.vll0 ~]$
```
Reviewed By: JasonHanwen
Differential Revision: D33994011
fbshipit-source-id: 8e6224c6e942e91c3403f686c8f0937d1002ed41
(cherry picked from commit a7014dd4029308c95007f362a57c31796d686647)
Do not assign dim_param for sequence tensor type.
Sequence of tensors could differ in dimension size.
Use a dimension with neither dim_value nor dim_param set
to denote an unknown dimension.
Create and assign dim_param for normal tensor type.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/70651
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/72547
toTuple() returns a new intrusive pointer that bumps its underlying ref count. Whereas, toTupeRef returns a reference. We can save an unnecessary ref count bump.
Based on https://fb.workplace.com/groups/pytorch.edge.team/permalink/1021780808376658/
similar to D34047666 (85d7e73a8a)
ghstack-source-id: 148665193
Test Plan:
```
> Executing task: buck: buck test //xplat/caffe2:test_lite_interpreter --config client.id=nuclide <
Executing in directory: /data/users/pavithran/fbsource
buck test //xplat/caffe2:test_lite_interpreter --config client.id=nuclide
clang-9: warning: argument unused during compilation: '-pthread' [-Wunused-command-line-argument]
Parsing buck files: finished in 2.1 sec
Creating action graph: finished in 0.5 sec
[RE] Metadata: Session ID=[reSessionID-66858379-0761-4966-a933-bc7f0d0add95]
[RE] Waiting on 0 remote actions. Completed 523 actions remotely, action cache hit rate: 0.00%.
Downloaded 3947/5089 artifacts, 20.92 Mbytes, 12.5% cache miss (for updated rules)
Building: finished in 01:04.0 min (100%) 5438/5438 jobs, 5192/5438 updated
Total time: 01:06.6 min
Testing: finished in 06:53.7 min (71 PASS/0 FAIL)
BUILD SUCCEEDED
RESULTS FOR //xplat/caffe2:test_lite_interpreter
PASS 406.0s 71 Passed 0 Skipped 0 Failed //xplat/caffe2:test_lite_interpreter
TESTS PASSED
Terminal will be reused by tasks, press any key to close it.
```
Reviewed By: kimishpatel
Differential Revision: D34082609
fbshipit-source-id: 4bcbdb2d11dd4c3bc392010487dccd2270278222
(cherry picked from commit dd64eb386d)
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 81b956c23a)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/68490
The use of ATEN as a fallback operator during ONNX conversion is important for increasing operator coverage or even provide more efficient implementations over some ONNX ops.
Currently this feature is available through `OperatorExportTypes.ONNX_ATEN_FALLBACK`,
but it also performs changes to the graph that are runnable by Caffe2, only.
This PR introduces restricts caffe2-specific graph transformations for `ONNX_ATEN_FALLBACK`
operator export type for when pytorch is built with caffe2 support (aka BUILD_CAFFE2=1 during build)
The first version of this PR introduced a new operator export type `ONNX_ATEN__STRICT_FALLBACK`,
which essentially is the same as `ONNX_ATEN_FALLBACK` but without caffe2 transformations.
It was preferred to not introduce a new operator export type, but to refine the existing aten fallback one
## BC-breaking note
### The global constant `torch.onnx.PYTORCH_ONNX_CAFFE2_BUNDLE` is removed in favor of
a less visible `torch.onnx._CAFFE2_ATEN_FALLBACK`.
`PYTORCH_ONNX_CAFFE2_BUNDLE` is really a dead code flag always set to False.
One alternative would be fixing it, but #66658 disables Caffe2 build by default.
Making a Caffe2 feature a private one seems to make more sense for future deprecation.
### The method `torch.onnx.export` now defaults to ONNX when `operator_export_type` is not specified.
Previously `torch.onnx.export's operator_export_type` intended to default to `ONNX_ATEN_FALLBACK` when `PYTORCH_ONNX_CAFFE2_BUNDLE` was set, but it would never happen as `PYTORCH_ONNX_CAFFE2_BUNDLE` is always undefined
Co-authored-by: Nikita Shulga <nshulga@fb.com>
Test Plan: Imported from OSS
Reviewed By: jansel
Differential Revision: D32483781
Pulled By: malfet
fbshipit-source-id: e9b447db9466b369e77d747188685495aec3f124
(cherry picked from commit 5fb1eb1b19)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/72349
1. Interface call'd methods need to be registered to class. Previously all interface calls are inlined so there was no such problem.
2. parseDoubleList and parseBoolList got reversed when refactoring.
Test Plan:
1. Get ASR's test model at
```
mkdir ~/asr1 && cd ~/asr1
fbpkg fetch speech.tuna.milan.ondevice.en_us
```
2. Convert model:
```
cd ~/fbsource
buck run //xplat/caffe2/fb/lite_predictor:convert_model -- --model=$HOME/asr1/pytorchmodel.pt --output_name=$HOME/asr1/pytorchmodel.ff
```
3. Ran lite_predictor_flatbuffer
```
buck run //xplat/caffe2/fb/lite_predictor:lite_predictor_flatbuffer -- --model=$HOME/asr1/pytorchmodel.ff --method_to_call=encode_src --method_to_generate_input=get_all_bundled_inputs_for_encode_src
```
See perf metric generated (means loading and inference succeeded).
Reviewed By: gmagogsfm, zhxchen17
Differential Revision: D33959746
fbshipit-source-id: 24671e1189438119f477032eb6c29bd7736e74ca
(cherry picked from commit 5e18809350)
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 6d65049ae5)
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 9732a52ed2)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/70201
Included functions:
save_mobile_module -> saves a mobile::Module to flatbuffer
load_mobile_module_from_file -> loads a flatbuffer into mobile::Module
parse_mobile_module -> parses from bytes or deserialized flatbuffer module object
Compared to previous attempts, this diff only adds flatbuffer to cmake target and leaves fbcode/xplat ones unchanged.
Test Plan: unittest
Reviewed By: malfet, gmagogsfm
Differential Revision: D33239362
fbshipit-source-id: b9ca36b83d6af2d78cc50b9eb9e2a6fa7fce0763
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/70212
Use DynamicType instead of ListType all over the place in Lite Interpreter. Namely we need to modify the following places:
1. Type parser which produces the Type constants.
2. IValue::type() which returns reflected Type from IValues.
3. Helper functions to construct the container value.
4. Typechecks which test whether a type instance is a particular container type.
ghstack-source-id: 146818619
Test Plan: CI
Reviewed By: iseeyuan
Differential Revision: D33176931
fbshipit-source-id: 9144787f5fc4778538e5c665946974eb6171a2e6
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/70202
Use DynamicType instead of DictType all over the place in Lite Interpreter. Namely we need to modify the following places:
1. Type parser which produces the Type constants.
2. IValue::type() which returns reflected Type from IValues.
3. Helper functions to construct the container value.
4. Typechecks which test whether a type instance is a particular container type.
ghstack-source-id: 146735648
Test Plan: no behavior change.
Reviewed By: iseeyuan
Differential Revision: D33137257
fbshipit-source-id: 971bf431658c422ea9353cc32cdab66e98876e9d
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/70338
Today Unpickler is used by both server and mobile for deserializing model, and it always fallback to mobile parser when there's no type resolver provided by user. However this is not intended as server and mobile type parser supports different things. In this diff we provide a default fallback using script parser and opt it out for all mobile cases.
ghstack-source-id: 146727330
(Note: this ignores all push blocking failures!)
Test Plan: CI
Reviewed By: iseeyuan
Differential Revision: D33284352
fbshipit-source-id: 997c4f110b36eee6596e8f23f6a87bf91a4197ed
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/68136
DynamicType is an extension to existing server JIT types. Today using normal server types on Edge is a bit problematic because in embedded environments we don't need the full spectrum of types but we still build with these unneeded dependencies.
Is it possible to just get rid of unneeded JIT types from Edge builds? It's not easy to do so at this moment. For example, on Edge we don't support Union type, but we have to pull in the dependency of Union type because Optional type is being supported which inherits from Union type, so Union type has to be included in the build. Although we could split Union type and Optional type, it could be argued that the root cause is every time we use anything inheriting from `c10::Type`, we don't have the direct evidence of how much dependency we pull in, because we do virtual calls and we don't know what exactly we're calling with server JIT types. If we don't know, it's highly possible that the linker doesn't know either so it cannot effectively strip unused methods.
To address this problem, one option is to implement a separate `DynamicType` which has simpler behavior and doesn't store different types as different symbols in binary but rather raw data (or "tag"). This could increase the binary size by several KBs, so I included several binary size reductions in the same stack, hoping at least we don't regress the binary size.
Currently `DynamicType` inherits from `c10::Type` because I want to reduce the migration cost of `DynamicType` by making it interfacing with existing server JIT types. In the future `DynamicType` should be implemented as a separate class without relying on `c10::Type` to make things both simpler and leaner.
ghstack-source-id: 146670522
Test Plan: in the next diff.
Reviewed By: VitalyFedyunin
Differential Revision: D32264615
fbshipit-source-id: 180eb0998a14eacc1d8b28db39870d84fcc17d5b
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:
- PyTorch and ONNX has supported BFloat16, add this to unblock some mixed-precision training model.
- Support PyTorch TNLG model to use BFloat16 tensors for the inputs/outputs of the layers that run on the NPU.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/66788
Reviewed By: jansel
Differential Revision: D32283510
Pulled By: malfet
fbshipit-source-id: 150d69b1465b2b917dd6554505eca58042c1262a
Summary:
Follow up to https://github.com/pytorch/pytorch/issues/68095
This also changes the files from the ATen folder to include c10's `Export.h` instead since they can't ever be exporting `TORCH_PYTHON_API`.
cc pietern mrshenli pritamdamania87 zhaojuanmao satgera rohan-varma gqchen aazzolini osalpekar jiayisuse SciPioneer H-Huang
Pull Request resolved: https://github.com/pytorch/pytorch/pull/69585
Reviewed By: mrshenli
Differential Revision: D32958594
Pulled By: albanD
fbshipit-source-id: 1ec7ef63764573fa2b486928955e3a1172150061
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/67787
First noticed in https://fb.workplace.com/groups/pytorch.edge.team/posts/952737705280969/ - basically one of the speech models has ~400 0 byte tensor files, so we're basically paying the cost of looking it up in the archive and reading nothing from it.
Turns out that there's a fairly simple fix to avoid reading a 0 byte tensor. Once we notice that it's 0 bytes, just use the default `DataPtr` instead to initializing it with 0 bytes read in from the input file stream.
ghstack-source-id: 142025211
Test Plan: CI and manually ran a couple production mobile models with bundled inputs. CI Will run all prod. mobile mobiles with bundled inputs.
Reviewed By: swolchok
Differential Revision: D32054983
fbshipit-source-id: 919b0cdbc44bccb8f6cfe0da10ff5474af37fd99
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/67803
* Addresses comments from #63589
[ONNX] remove torch::onnx::PRODUCER_VERSION (#67107)
Use constants from version.h instead.
This simplifies things since we no longer have to update
PRODUCER_VERSION for each release.
Also add TORCH_VERSION to version.h so that a string is available for
this purpose.
[ONNX] Set `ir_version` based on opset_version. (#67128)
This increases the odds that the exported ONNX model will be usable.
Before this change, we were setting the IR version to a value which may
be higher than what the model consumer supports.
Also some minor clean-up in the test code:
* Fix string replacement.
* Use a temporary file so as to not leave files around in the test
current working directory.
Test Plan: Imported from OSS
Reviewed By: msaroufim
Differential Revision: D32181306
Pulled By: malfet
fbshipit-source-id: 02f136d34ef8f664ade0bc1985a584f0e8c2b663
Co-authored-by: BowenBao <bowbao@microsoft.com>
Co-authored-by: Gary Miguel <garymiguel@microsoft.com>
Co-authored-by: Nikita Shulga <nshulga@fb.com>
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/66140
* Add new argument to export api to enable users specifying `nn.Module` classes that they wish to be exported as local function in ONNX model.
* Refactor `torch/csrc/jit/serialization/export.cpp`, and remove redundant `EncoderBase` class.
* ~~Contains changes from #63268~~
* Depends on #63716 to update onnx submodule.
Test Plan: Imported from OSS
Reviewed By: jansel
Differential Revision: D31424098
fbshipit-source-id: c949d0b01c206c30b4182c2dd1a5b90e32b7a0d3
Co-authored-by: BowenBao <bowbao@microsoft.com>
Summary:
This would save the cost copying text from stack to heap in some cases (like
parsing function schema during loading phase of libtorch.so)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/65309
Reviewed By: swolchok
Differential Revision: D31060315
Pulled By: gmagogsfm
fbshipit-source-id: 0caf7a688b40df52bb4388c5191d1a42351d6f1a
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/66693
Passing a `TypePtr` by value causes an unnececssary refcount
bump. We don't need to take ownership, so `const Type&` is all we
need.
I considered providing a compatibility shim that takes `const
TypePtr&`, but doing so is dangerous because a
copy is required to convert from a more specific pointer like
`NoneTypePtr`.
ghstack-source-id: 140737081
Test Plan: CI
Reviewed By: suo
Differential Revision: D31691869
fbshipit-source-id: f766ce3234a28771c2a9ca4c284eb3f96993a3d0
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64066
I noticed a bunch of time being spent heap-allocating Tuples
in the unpickler. 1-, 2-, and 3-element Tuples are apparently common
enough that they get their own bytecode instructions, so I decided to
try also giving them their own representation. We store up to 3
IValues inline in `Tuple` rather than doing a second heap allocation
for a `std::vector<IValue>`.
ghstack-source-id: 140695395
Test Plan:
Added automated tests for TupleElements.
Pixel 3 before: https://www.internalfb.com/intern/aibench/details/761596366576284
Pixel 3 after: https://www.internalfb.com/intern/aibench/details/591414145082422
We went from 347 ms to 302 ms.
Reviewed By: dhruvbird
Differential Revision: D30592622
fbshipit-source-id: 93625c54c9dca5f765ef6d5c191944179cb281a8
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/65345
FooType::get() can return a const reference. Inconveniently, converting shared_ptr<FooType> to shared_ptr<Type> requires a copy & refcount bump, so to properly take advantage of this in unshapedType() we need to take a const Type& in isSubtypeOf(), which is good practice anyway -- don't require a shared_ptr if you don't need to take ownership.
ghstack-source-id: 140044165
Test Plan:
CI
perf says c10::unshapedType time decreased from 2.8% to 2.2% during static runtime startup, though I expect this to be generally beneficial.
Reviewed By: hlu1
Differential Revision: D31027361
fbshipit-source-id: 676feb81db9f74ad7b8651d8774f4ecb4cfa6ab8
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/65346
Tidying up the top sources of reference count decrements seen during static runtime startup.
ghstack-source-id: 140027349
Test Plan:
CI
perf now shows under 2% time spend in ~__shared_count instead of about 5%.
Reviewed By: suo
Differential Revision: D31057277
fbshipit-source-id: 9a16daf2e655fda80d4ec21290b30f02ba63d8da
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:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64382
* This `use_external_data_format` parameter is used for large models cannot be exported because of the 2GB protobuf limit.
* When `use_external_data_format` set to True, the model is exported in ONNX external data format, in which case some of the model parameters are stored in external binary files and not in the ONNX model file itself.
* This PR will set this paramter to DEPRECATED and check the model proto sizes by code instead of by user, if the sizes lager than 2GB, then `use_external_data_format = True` automatically.
Test Plan: Imported from OSS
Reviewed By: ezyang
Differential Revision: D30905265
Pulled By: malfet
fbshipit-source-id: 82b4e17bfa6a8de2bfd700a5282c12f6835603cb
Co-authored-by: hwangdeyu <dejack953@outlook.com>
Summary:
The source is shared across all threads running the torchscript
interpreter, so if several threads encounter errors at once, they will all race
to unpickle the source, leading to memory corruption.
Test Plan:
Model 217993215_0 is the problematic model; I wasn't able to repro
the crash with requests stored in Hive, but I could easily by adding my
devserver (SMC tier predictor.bertrand) as a shadow tier to the model's tier
(inference_platform.predictor_model.prod.bi.217993215_latest). (i.e., set
shadow_tier property to predictor.bertrand=1 to proxy 1% of traffic).
With this diff, the ASAN/TSAN errors go away.
Reviewed By: suo
Differential Revision: D31044009
fbshipit-source-id: 56f9ef3880e7cf09f334db71b4256e362b4de965
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
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/61862
Modularize functions of parsing bytecode tables so that they can be used as needed in situations other than mobile lite interpreter.
* The decoupled functions are re-used by current lite interpreter loader.
* The bytecode can be serialized/deserialized from other formats.
* The decoupled functions have minimum dependencies on other PyTorch components.
Next:
Build a driver binary to include the parser and interpreter, but only has necessary dependency on other PyTorch components.
ghstack-source-id: 137867287
Test Plan:
As an example, a simple bytecode is parsed to a mobile function, and directly run in the added unit test, `RunTimeTest:ParseBytecode`. It contains basic control flow (if, else) and basic data orchestration (list construction).
CI
Reviewed By: larryliu0820
Differential Revision: D29798382
Pulled By: iseeyuan
fbshipit-source-id: 1c173a5f5d37097e3a97baec3f3e48e1eea1400f
Summary:
This PR is created to replace https://github.com/pytorch/pytorch/pull/53180 PR stack, which has all the review discussions. Reason for needing a replacement is due to a messy Sandcastle issue.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64234
Reviewed By: gmagogsfm
Differential Revision: D30656444
Pulled By: ansley
fbshipit-source-id: 77536c8bcc88162e2c72636026ca3c16891d669a
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/63974
Saw some time spent in this for model loading, no reason not to move here.
ghstack-source-id: 136760979
Test Plan: Re-profile model loading on devserver; IValue copy ctor time has gone down
Reviewed By: dhruvbird
Differential Revision: D30548923
fbshipit-source-id: 42000f2e18582762b43353cca10ae094833de3b3
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/62794
This pr updates jit serialization to support pickling Sparse COO tensors.
This pr updates message.cpp to support Sparse COO tensors.
A bug was filed a few years ago https://github.com/pytorch/pytorch/issues/30807.
I tested the fix by adding sparse tensor tests to rpc_test.py and dist_autograd_test.py.
cc pietern mrshenli pritamdamania87 zhaojuanmao satgera rohan-varma gqchen aazzolini osalpekar jiayisuse agolynski SciPioneer H-Huang mrzzd cbalioglu gcramer23 gmagogsfm
Test Plan: Imported from OSS
Reviewed By: soulitzer
Differential Revision: D30608848
Pulled By: gcramer23
fbshipit-source-id: 629ba8e4a3d8365875a709c9b87447c7a71204fb
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/63576
We serialize function name associated with InlinedCallStackPtr. This is derived
via querying Function* stored in InlinedCallStack. However this is a raw
pointer that is not gauranteed to be valid when we serialization happens. On
the other hand we also store function name separately when constructing
InlinedCallStack anyways. So this change just uniformly relies on function_name
instead of Function*
Test Plan: Internal build's asan failure + CI
Reviewed By: larryliu0820
Differential Revision: D30427029
fbshipit-source-id: de9617482404785920ed2e67b72f38461590fba3
Summary:
Add `-Wno-writable-strings`(which is clang's flavor of `-Wwrite-strings`) to list of warnings ignored while compiling torch_python.
Avoid unnecessary copies in range loop
Fix number of signed-unsigned comparisons
Found while building locally on M1
Pull Request resolved: https://github.com/pytorch/pytorch/pull/62930
Reviewed By: albanD
Differential Revision: D30171981
Pulled By: malfet
fbshipit-source-id: 25bd43dab5675f927ca707e32737ed178b04651e
Summary:
Replace for loop with for `irange` loop. Also fix some unused variable warnings in range loop cases
Pull Request resolved: https://github.com/pytorch/pytorch/pull/62928
Reviewed By: driazati
Differential Revision: D30171904
Pulled By: malfet
fbshipit-source-id: 1b437a0f7e3515f4a2e324f3450e93312f1933ae
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/61933
### Issue:
SubModules with same name are not serialized correctly in bytecode format while using `_save_for_mobile`. These submodules are not distinguished as different modules even though they have different foward, setstate etc if they have the same name.
### Fix:
Mangler creates unique names so that modules and submodules that have same names can be uniquely identified while saving the module. iseeyuan rightly pointed out the underlying issue that mangler is not used in the process of saving bytecode and hence unique references for the submodules are not created. Please refer to the notebook to repro the issue: N777224
### Diff:
The above idea of fix is implemented. The mangled names are used in bytecode thereby the files in `code/` directory now have right reference to the `bytecode.pkl`
Will this have backward compatibility?
iseeyuan please feel free to correct or update this.
Yes. This fix impacts only modules with same name sub modules which were not serialized correctly before. Existing modules should have correct references and `_load_for_mobile` must not see any change. To confirm this the existing test cases need to pass for the diff to be approved and shipped.
ghstack-source-id: 134242696
Test Plan:
```
~/fbsource/fbcode > buck test caffe2/test/cpp/jit:jit -- BackendTest.TestCompositeWithSetStates
Downloaded 0/5 artifacts, 0.00 bytes, 100.0% cache miss (for updated rules)
Building: finished in 19.2 sec (100%) 17619/17619 jobs, 3/17619 updated
Total time: 19.5 sec
More details at https://www.internalfb.com/intern/buck/build/91542d50-25f2-434d-9e1a-b93117f4efe1
Tpx test run coordinator for Facebook. See https://fburl.com/tpx for details.
Running with tpx session id: de9e27cf-4c6c-4980-8bc5-b830b7c9c534
Trace available for this run at /tmp/tpx-20210719-161607.659665/trace.log
Started reporting to test run: https://www.internalfb.com/intern/testinfra/testrun/844425127206388
✓ ListingSuccess: caffe2/test/cpp/jit:jit - main (8.140)
✓ Pass: caffe2/test/cpp/jit:jit - BackendTest.TestCompositeWithSetStates (0.528)
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/844425127206388
```
```
~/fbsource/fbcode > buck test caffe2/test/cpp/jit:jit -- BackendTest.TestConsistencyOfCompositeWithSetStates
Building: finished in 4.7 sec (100%) 6787/6787 jobs, 0/6787 updated
Total time: 5.0 sec
More details at https://www.internalfb.com/intern/buck/build/63d6d871-1dd9-4c72-a63b-ed91900c4dc9
Tpx test run coordinator for Facebook. See https://fburl.com/tpx for details.
Running with tpx session id: 81023cd2-c1a2-498b-81b8-86383d73d23b
Trace available for this run at /tmp/tpx-20210722-160818.436635/trace.log
Started reporting to test run: https://www.internalfb.com/intern/testinfra/testrun/8725724325952153
✓ ListingSuccess: caffe2/test/cpp/jit:jit - main (7.867)
✓ Pass: caffe2/test/cpp/jit:jit - BackendTest.TestConsistencyOfCompositeWithSetStates (0.607)
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/8725724325952153
```
To check the `bytecode.pkl` using module inspector please check:
N1007089
Reviewed By: iseeyuan
Differential Revision: D29669831
fbshipit-source-id: 504dfcb5f7446be5e1c9bd31f0bd9c986ce1a647
Summary:
As GoogleTest `TEST` macro is non-compliant with it as well as `DEFINE_DISPATCH`
All changes but the ones to `.clang-tidy` are generated using following script:
```
for i in `find . -type f -iname "*.c*" -or -iname "*.h"|xargs grep cppcoreguidelines-avoid-non-const-global-variables|cut -f1 -d:|sort|uniq`; do sed -i "/\/\/ NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)/d" $i; done
```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/62008
Reviewed By: driazati, r-barnes
Differential Revision: D29838584
Pulled By: malfet
fbshipit-source-id: 1b2f8602c945bd4ce50a9bfdd204755556e31d13
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/61806
Currently, if you do `save_pickle` on a ScriptModule, then `save_pickle`
on a tensor, this would result in a `0.storage` tensor being written
*twice* to the zip archive. This would cause weird bugs on the
serializing side (this presented as a ASAN-detected heap buffer overflow
because we tried to read more memory from a tensor than we actually
had).
Turns out this was because when we did:
```
self.storage_context = self.script_module_serializer.storage_context()
```
it returned a new copy of the storage context, so we weren't actually
assigning unique names to tensors!!
This PR fixes the issue by making `(De)SerializationStorageContext`
non-copyable and fixing up the parts of the bindings that returned by
copy.
Differential Revision:
D29748969
D29748969
Test Plan: Imported from OSS
Reviewed By: Lilyjjo
Pulled By: suo
fbshipit-source-id: c2f89ab270e07e7a111fb35c545b5e07b804dc3c
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/61760
Remove all code that related to metadata.pkl creation including creating metadata.pkl, converting data from extra/mobile_info.json and extra/producer_info.json to metadata.pkl file.
Test Plan:
## Run buck commands:
- `cd` into `fbcode` then `buck build //caffe2/caffe2/fb/init:init`
- `cd` into `fbcode` then `buck build //caffe2/torch/fb/init:init`
- `buck build //xplat/caffe2:torch_mobile_core`
## Export a PyTorch lite/mobile model
- Run: `flow-cli canary users.xcheng16.pytorch_trainer.TestWorkflow --run-as-secure-group ai_mobile_platform --buck-target //fblearner/flow/projects/users/xcheng16:workflow` under `fbcode` on devserver.
- Resulted Model: metadata.pkl no longer exist
{F632063134}
Reviewed By: guangy10
Differential Revision: D29702943
fbshipit-source-id: ec7964f4aa3a8e09ccc20b1a7e2232f85931dd81
Summary:
* Minor: spelling, grammar.
* Add calls to `GRAPH_DUMP()` where they were missing.
* Add or expand a few comments.
* Move a few comments to seemingly more appropriate spots.
* In canonicalize_graph_fuser_ops.cpp inline `runnableInputs()` since it
was only called in one place and had a misleading comment and
confusing name.
* In `PeepholeOptimizeImpl::optimizeBlock()`, set `changed = true;` when
removing `aten::is_complex`. Pretty sure its absence was a bug.
* Delete unused `_jit_pass_remove_inplace_ops` and and its
implementation `RemoveInplaceOps()`.
* In `preprocessCaffe2Ops()`, remove redundant check for nested optional
types. It was already checked in `checkONNXCompatibility()`.
* In `EncoderBase::AddAttribute`, log the unexpected attribute kind.
I don't remember the repro case now but I did hit this error at some
point and this additional logging made it easier to understand.
* In `fuseConvBatchNorm()` in eval_peephole.cpp, consistently use
camelCase instead of snake_case for local variables.
* Add curly braces around the bodies of if and loops.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/60390
Reviewed By: Krovatkin
Differential Revision: D29523283
Pulled By: SplitInfinity
fbshipit-source-id: 4e16c5648616f53da07d68dab7fdf252e06a0752
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/60244
Do 2GB size check for protocol buffer serialization at a later time, to avoid false alarming for cases like shape inference where no serialization actually happens.
Test Plan: Imported from OSS
Reviewed By: zou3519, ZolotukhinM
Differential Revision: D29494910
Pulled By: SplitInfinity
fbshipit-source-id: 4c36d26de9a94e5d6cf78f332d4dffc46588ebf0
Co-authored-by: BowenBao <bowbao@microsoft.com>
Summary:
This PR suppresses clang-tidy warnings in the codebase (for now) so that we can re-enable clang-tidy checks on master.
I ran this script to add the `NOLINTNEXTLINE` comments (on a devserver):
```bash
python3 setup.py develop
# Uses same script that's run on CI and adds the -j (parallel), -s (add comments), -k (continue if diagnostic errors are found) options
python3 tools/clang_tidy.py \
-j \
-s \
-k \
-v \
--paths torch/csrc/ \
-g"-torch/csrc/jit/passes/onnx/helper.cpp" \
-g"-torch/csrc/jit/passes/onnx/shape_type_inference.cpp" \
-g"-torch/csrc/jit/serialization/onnx.cpp" \
-g"-torch/csrc/jit/serialization/export.cpp" \
-g"-torch/csrc/jit/serialization/import.cpp" \
-g"-torch/csrc/jit/serialization/import_legacy.cpp" \
-g"-torch/csrc/onnx/init.cpp" \
-g"-torch/csrc/cuda/nccl.*" \
-g"-torch/csrc/cuda/python_nccl.cpp" \
-g"-torch/csrc/autograd/FunctionsManual.cpp" \
-g"-torch/csrc/generic/*.cpp" \
-g"-torch/csrc/jit/codegen/cuda/runtime/*" \
-g"-torch/csrc/deploy/interpreter/interpreter.cpp" \
-g"-torch/csrc/deploy/interpreter/interpreter.h" \
-g"-torch/csrc/deploy/interpreter/interpreter_impl.h" \
-g"-torch/csrc/deploy/interpreter/test_main.cpp"
```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/60649
Test Plan: Verified changes by re-running the script (without the `-s` option) and seeing no warnings/errors.
Reviewed By: walterddr, janeyx99
Differential Revision: D29504258
Pulled By: 1ntEgr8
fbshipit-source-id: 78310b30ee8213b73ddb4771ad874665323e7a4e
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/59735
1. Fixes ABA storage identity problem during serialization for `torch.package` by keeping reference of serialized storages through lifetime of `PackageExporter` to prevent reuse of memory address. Achieved by extending logic used in solution to mobile's same issue.
2. Adds determinism to naming scheme of serialized storages in export code paths which utilize `tensor_cdata_naming_scheme`(introduced 2nd mapping in `StorageContext`, now maps `storage cdata ptr` -> `unique id`, `unique id` -> `c10::Storage`)
3. Additionally uses presence of a storage in the `StorageContext` instance as marker for if a storage has been serialized or not, removing the need to scan the `PythonStreamWriter` for presence of the storage's serialization file
Test Plan: Imported from OSS
Reviewed By: suo
Differential Revision: D29075276
Pulled By: Lilyjjo
fbshipit-source-id: 15a5c30b1de99c5bd7079388f2db9b6ece2eca12
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/58852
Enable implicit operator versioning via number of arguments from Mobile.
1. By default, TS doesn't emit instructions for tailing default args and the provided number of specified args is serialized to bytecode. From interpreter the default values are fetched from operator schema. The implementation has been landed in #56845. Please refer to #56845 for details.
2. Since there is bytecode schema change, the bytecode version is bumped from 5 to 6.
3. The corresponding backport function is provided, for forward compatibility use. Note that because there is instruction change, a global flag is used as the switch to control the two versions.
Test Plan: Imported from OSS
Reviewed By: raziel
Differential Revision: D28789746
Pulled By: iseeyuan
fbshipit-source-id: 6e5f16460c79b2bd3312de02d0f57b79f50bf66b
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/59722
Reintroduce sharing constant between bytecode and torchscript (same as #58629) after the fix#59642
Test Plan: Imported from OSS
Reviewed By: iseeyuan
Differential Revision: D29002345
Pulled By: cccclai
fbshipit-source-id: d9c8e474ff57d0509580183206df038a24ad27e3
Summary:
Make an assert message in Pytorch's JIT provide better information by
printing the debug name of a value in `PythonPrintImpl::useOf` if it's not
found in any tables.
Test Plan:
Tested printing a `module.code` where the module had an invalid value used
as an operand. Before it asserted without any more details, afterwards it
printed the debug name which made it easy to track down the offending value.
Reviewed By: SplitInfinity
Differential Revision: D28856026
fbshipit-source-id: 479f66c458a0a2d9a161ade09f20382e7b19d60e
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/57481
This diff introduces function name to InlinedCallStack.
Since we are using InlinedCallStack for debug information in lite
interpreter as well as delegate backends, where InlinedCallStack cannot
be constructed from model source code, we need to save function name.
In the absence of function name Function* is used to get name of the
function. This is when JIT compiles code at runtime.
When that is not possible, this diff introduces a way to obtain function
name.
Test Plan:
test_backend
test_cs_debug_info_serialization
test_backend
test_cs_debug_info_serialization
Imported from OSS
Differential Revision:
D28159097
D28159097
Reviewed By: raziel, ZolotukhinM
Pulled By: kimishpatel
fbshipit-source-id: deacaea3325e27273f92ae96cf0cd0789bbd6e72
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/57441
debug info
Previous diffs did not save operator name in debug info. For delegated
backends that only idenfity op for profiling with debug handle, operator
name should be stores as well.
Furthermore to complete debug informaton also serialize function name.
Test Plan:
Existing lite interpreter and backend tests
Existing lite interpreter and backend tests
Imported from OSS
Differential Revision:
D28144581
D28144581
Reviewed By: raziel
Pulled By: kimishpatel
fbshipit-source-id: 415210f147530a53b444b07f1d6ee699a3570d99
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/55462
handles and symbolicate exception callstack thrown from backend.
Objective of this diff is to achieve improve error reporting when
exceptions are raised from lowered backend. We would effectively like to
get the same model level stack trace that you would get without having
lowered some module to backend.
For example:
```
class AA(nn.Module):
def forward(self, x, y):
return x + y
class A(nn.Module):
def __init__(...):
self.AA0 = AA()
def forward(self, x, y):
return self.AA0.forward(x, y) + 3
class B(nn.Module):
def forward(self, x):
return x + 2
class C(nn.Module):
def __init__(...):
self.A0 = A()
self.B0 = B()
def forward(self, x, y):
return self.A0.forward(x, y) + self.B0.forward(x)
```
If the we then do C().forward(torch.rand((2,3)), torch.rand(14,2))) we
will likely see error stack like:
```
C++ exception with description "The following operation failed in the TorchScript interpreter.
Traceback of TorchScript (most recent call last):
File "<string>", line 3, in forward
def forward(self, x, y):
return self.A0.forward(x, y) + self.B0.forward(x)
~~~~~~~~~~~~~~~ <--- HERE
File "<string>", line 3, in forward
def forward(self, x, y):
return self.AA0.forward(x, y) + 3
~~~~~~~~~~~~~~~~ <--- HERE
File "<string>", line 3, in forward
def forward(self, x, y):
return x + y
~~~~~ <--- HERE
```
We would like to see the same error stack if we lowered C.A0 to some
backend.
With this diff we get something like:
```
Module hierarchy:top(C).A0(backend_with_compiler_demoLoweredModule).AA0(AA)
Traceback of TorchScript (most recent call last):
File "<string>", line 3, in FunctionName_UNKNOWN
def forward(self, x, y):
return self.A0.forward(x, y) + self.B0.forward(x)
~~~~~~~~~~~~~~~ <--- HERE
File "<string>", line 5, in FunctionName_UNKNOWN
typed_inputs: List[Any] = [x, y, ]
if self.__backend.is_available() :
_0, = self.__backend.execute(self.__handles["forward"], typed_inputs)
~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
assert isinstance(_0, Tensor)
return _0
File "<string>", line 3, in FunctionName_UNKNOWN
def forward(self, x, y):
return self.AA0.forward(x, y) + 3
~~~~~~~~~~~~~~~~ <--- HERE
File "<string>", line 3, in FunctionName_UNKNOWN
def forward(self, x, y):
return x + y
~~~~~ <--- HERE
```
This is achieved in 3 parts:
Part 1:
A. BackendDebugInfoRecorder:
During backend lowering, in `to_backend`, before calling the preprocess
function corresponding to the backend. This will facilitate recording of
debug info (such as source range + inlined callstack) for the lowered module.
B. Instantiate WithBackendDebugInfoRecorder with BackendDebugInfoRecorder.
This initializes thread local pointer to BackendDebugInfoRecorder.
C. generate_debug_handles:
In preprocess function, the backend will call generate_debug_handles
for each method being lowered separately. generate_debug_handles
takes `Graph` of the method being lowered and returns a map
of Node*-to-debug_handles. Backend is responsible for storing debug
handles appropriately so as to raise exception (and later profiling)
using debug handles when the exception being raised corresponds to
particular Node that was lowered.
Inside generate_debug_handles, we will query the current
BackendDebugHandleInfoRecorder, that is issuing debug handles. This debug
handle manager will issue debug handles as well as record
debug_handles-to-<source range, inlined callstack> map.
D. Back in `to_backend`, once the preprocess function is has finished
lowering the module, we will call `stopRecord` on
BackendDebugInfoRecorder. This will return the debug info map. This
debug info is then stored inside the lowered module.
Part 2:
Serialization:
During serialization for bytecode (lite interpreter), we will do two
things:
1. Extract all the source ranges that are contained inside
debug_handles-to-<source range, inlined callstack> map for lowered
module. This will be source range corresponding to debug handles,
including what is there is inlined callstack. Since we replaced original
module with lowered module, we wont be serializing code for the original
module and thus no source range. That is why the source range will have
to be stored separately. We will lump all the source ranges for all the
lowered modules in one single debug_pkl file.
2. Then we will serialize debug_handles-to-<source range, inlined
callstack> map.
Now during deserialization we will be able to reconstruct
debug_handles-to-<source range, inlined callstack> map. Given all
debug_handles are unique we would not need any module information.
Test Plan:
Tests are added in test_backend.cpp
Tests are added in test_backend.cpp
Imported from OSS
Differential Revision:
D27621330
D27621330
Reviewed By: raziel
Pulled By: kimishpatel
fbshipit-source-id: 0650ec68cda0df0a945864658cab226a97ba1890
Summary:
As title, main change:
1. Enable share constant table and reduce model size up to 50%
2. Bump bytecode version from v4 to v5.
3. Add the unittest back. (It was partially removed because `script_module_v5.ptl` bytecode version is v5. When current runtime is v4 and try to load a v5 model, it will raise an error because version is not within the range.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/57888
As title
ghstack-source-id: 129255867
Test Plan:
CI
```
buck test papaya/toolkit/frontend/torch/...
buck test mode/opt papaya/integration/service/test/smartkeyboard:smartkeyboard_system_test
```
Reviewed By: raziel, iseeyuan
Differential Revision: D28309381
fbshipit-source-id: 6f5cf4296eaadde913d55f27d5bfb9d1dea2fbaf
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/58182
As title, the v5 model format will be
```
(base) chenlai@chenlai-mp reuse_constant % zipinfo /Users/chenlai/Documents/pytorch/reuse_constant/tmp/zip/script_module_v5_unify.ptl
Archive: /Users/chenlai/Documents/pytorch/reuse_constant/tmp/zip/script_module_v5_unify.ptl
Zip file size: 3120 bytes, number of entries: 7
-rw---- 0.0 fat 77 bl stor 80-000-00 00:00 script_module_v4_unify/data.pkl
-rw---- 0.0 fat 240 bl defN 80-000-00 00:00 script_module_v4_unify/code/__torch__/___torch_mangle_5.py
-rw---- 0.0 fat 422 bl defN 80-000-00 00:00 script_module_v4_unify/code/__torch__/___torch_mangle_5.py.debug_pkl
-rw---- 0.0 fat 64 bl stor 80-000-00 00:00 script_module_v4_unify/constants/140245072983168.storage
-rw---- 0.0 fat 172 bl stor 80-000-00 00:00 script_module_v4_unify/constants.pkl
-rw---- 0.0 fat 678 bl stor 80-000-00 00:00 script_module_v4_unify/bytecode.pkl
-rw---- 0.0 fat 2 bl stor 80-000-00 00:00 script_module_v4_unify/version
7 files, 1655 bytes uncompressed, 1453 bytes compressed: 12.2%
```
bytecode.pkl is:
```
(5,
('__torch__.___torch_mangle_5.TestModule.forward',
(('instructions',
(('STOREN', 1, 2),
('DROPR', 1, 0),
('LOADC', 0, 0),
('LOADC', 1, 0),
('MOVE', 2, 0),
('OP', 0, 0),
('LOADC', 1, 0),
('OP', 1, 0),
('RET', 0, 0))),
('operators', (('aten::add', 'int'), ('aten::add', 'Scalar'))),
('constants',
(torch._utils._rebuild_tensor_v2(pers.obj(('storage',
torch.DoubleStorage,
'140245072983168.storage',
'cpu',
8),),
0,
(2, 4),
(4, 1),
False,
collections.OrderedDict()),
1)),
('types', ()),
('register_size', 2)),
(('arguments',
((('name', 'self'),
('type', '__torch__.___torch_mangle_5.TestModule'),
('default_value', None)),
(('name', 'y'), ('type', 'int'), ('default_value', None)))),
('returns',
((('name', ''), ('type', 'Tensor'), ('default_value', None)),)))))
```
constants.pkl is:
```
(torch._utils._rebuild_tensor_v2(pers.obj(('storage', torch.DoubleStorage, '140245072983168.storage', 'cpu', 8),),
0,
(2, 4),
(4, 1),
False,
collections.OrderedDict()),)
```
Both tensors will refer to the tensor in at the path `script_module_v4_unify/constants/140245072983168.storage`.
## Note
According to unify format, all tensors will be written to the folder `.data`, however, torch.jit.load() can't handle the unified format at this moment, so this change will write tensors at the `constants` folders, and mobile will write/read tensors from `constants` folder. such that the model can be interpreted by both jit and mobile.
ghstack-source-id: 129010347
Test Plan: buck test mode/dev //caffe2/test/cpp/jit:jit
Reviewed By: raziel, iseeyuan
Differential Revision: D28375257
fbshipit-source-id: 6544472db4c957c5ea037e0bb5112b637dd15897
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/55958
This PR refactors the existing ScriptModuleSerializer to be exposed to the public. Most of the code is the same, git just thinks it's different due to it being shifted over a white space. I commented on the actual changes that weren't due to the white space shifting
Test Plan: Imported from OSS
Reviewed By: suo
Differential Revision: D27832546
Pulled By: Lilyjjo
fbshipit-source-id: c73e33211e46fca56053aa45ea2b9a2803eab82c
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/56845
Handle forward/backward compatibility caused by added default arguments in mobile. As an example,
In older version, operator aten::foo's schema is
```
foo(Tensor a, Tensor b) -> Tensor
```
In the new version, the schema is updated to
```
foo(Tensor a, Tensor b, int groups=1) -> Tensor
```
## Model file
Serialize the number of specified arguments to each operator into the bytecode operator table. Before the operator table contains operator name and overload name:
```
('operators', (('aten::foo', ''),))
```
Now the number of specified arguments is added:
```
# bytecode version 6
('operators', (('aten::foo', '', 2),))
```
where "2" means the number of specified arguments.
Since there's bytecode schema change, the bytecode version number is bumped. This PR is to be landed after #56002 , where the version number is bumped from 4 to 5. This PR bumps the version number from 5 to 6.
## Runtime and backward compatibility
When the operator is found (either jit or c10), we have the OperatorHandle, where the operator schema can be accessed by
```
op.value().schema().arguments()
```
Adaptation is implemented to handle backward compatibility. For the example above, the new runtime holds the updated schema:
```
foo(Tensor a, Tensor b, int groups=1) -> Tensor
```
Whereas the model file carries
```
(('aten::foo', ''), 2)
```
We can implement a wrapper around the original function pointer to push the default argument to the stack.
## Deliver time and forward compatibility
At model delivery time, two checks can be done:
### Operator check
Two APIs to be provided:
* Runtime: An API to get a runtime’s ops and their schemas (i.e. the # of args). D27920185(WIP)
* Model: An API to get a model’s ops and their schema requirements (i.e. the # of args required).
The APIs can be used to check
* runtime.ops() is a superset of model.ops()
* for each op in model.ops() validate their schemas are compatible with those in runtime.ops() -- i.e. the # args required in a model op are <= # args in the runtime op.
Note that only root ops in the model needs to be checked here. For transient ops it's not necessary. For example, if a root op, "aten::root" calls "aten::foo", it's "aten::root"'s responsibility to adapt to "aten::foo"'s change, or "aten::root" itself needs to be updated too.
### Bytecode version backport (PR coming)
When delivering a model with bytecode v6, if the runtime only works with bytecode v5 and lower, backport is needed.
* The number of arguments is removed from the operator table
* The bytecode version is changed from 6 to 5
Note that this backport is a pure format change, it does not guarantee the backported model always runs in old runtime. The operator check mentioned before should be done first, before it’s back ported to v5.
Test Plan: Imported from OSS
Reviewed By: gmagogsfm
Differential Revision: D27986544
Pulled By: iseeyuan
fbshipit-source-id: 143e19d4798cfb96b65095538dd648eead4e3fda
Summary:
## Note:
**This change will include the feature, but the feature is not on. It will be enabled and bytecode version will be bumped in D27844651 (8c04593c0a).**
Jit will generate constant tensor, and it locates in the constant folder (can find them after unzip model.ptl). Bytecode generated by lite interpreter also includes constant tensor, which are almost the same with the constant tensor value from jit. This pr will let lite interpreter reuses the constant tensor from jit, instead of reproducing the similar tensor values. The reading and writing session will be as following.
More details and background can found in [Lite Interpreter Model Size Issue](https://fb.quip.com/OSidAcjhL9LS).
Data size comparison can be found in [Model size analysis](https://fb.quip.com/oEm6A4bhbo06)
### Write
1. In `export_module.cpp`, store all constant tensor value from jit in an `unordered_map constants_from_jit`, where the tensor value use tensor string as a hash. constants_from_jit is a map: (tensor) => (archive_name, index). When writing bytecode archive `writeByteCode()`, the map `constants_from_jit` will also be passed all the way to it's pickler.
2. In `pickler.cpp`, a new map tensors_archive_table_ is added. It is also a map: (tensor) => (archive_name, index). The corresponding function to update the map is `updateTensorsArchiveTable`. When pushing the storage of a tensor, if the tensor exists in `tensors_archive_table_`, the root key will be `{archive_name}/{index}`, instead of `{index}`. For example, the tensor
```
torch._utils._rebuild_tensor_v2(pers.obj(('storage', torch.FloatStorage, '0', 'cpu', 90944),),
0,
(1, 116, 28, 28),
(90944, 784, 28, 1),
False,
collections.OrderedDict()),
```
will be like following instead
```
torch._utils._rebuild_tensor_v2(pers.obj(('storage', torch.FloatStorage, 'constants/0', 'cpu', 90944),),
0,
(1, 116, 28, 28),
(90944, 784, 28, 1),
False,
collections.OrderedDict()),
```
**Note**: Only tensors in bytecode archive will be different. The tensors in other archive remains the same, because `updateTensorsArchiveTable()` is only called when `use_tensors_archive_table_` is `true`, and `tensors_archive_table_` is only set as `true` when `bytecode_version` is a valid number.
### Read
1. In `import.cpp`, the function `read_record` passed to Unpickler is updated. The argument of `read_record` is the root key. In version 4, the root key will just be index, and `archive_name_plus_slash` + `name` will be used to get the tensor. With this change (version 5+), `read_record` will check if slash exists in the argument `name`. If it does, it means the argument is `archive_name/index`, and it can be used to get tensor directly.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/56002
ghstack-source-id: 128498244
Test Plan:
### Verify the new model generated from this pr can reuse constant table and the numerical result is the same.
1. Build pytorch locally. `MACOSX_DEPLOYMENT_TARGET=10.9 CC=clang CXX=clang++ USE_CUDA=0 DEBUG=1 MAX_JOBS=16 python setup.py develop`
2. Run `python save_lite.py`
```
import torch
# ~/Documents/pytorch/data/dog.jpg
model = torch.hub.load('pytorch/vision:v0.6.0', 'shufflenet_v2_x1_0', pretrained=True)
model.eval()
# sample execution (requires torchvision)
from PIL import Image
from torchvision import transforms
import pathlib
import tempfile
import torch.utils.mobile_optimizer
input_image = Image.open('~/Documents/pytorch/data/dog.jpg')
preprocess = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
input_tensor = preprocess(input_image)
input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model
# move the input and model to GPU for speed if available
if torch.cuda.is_available():
input_batch = input_batch.to('cuda')
model.to('cuda')
with torch.no_grad():
output = model(input_batch)
# Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
print(output[0])
# The output has unnormalized scores. To get probabilities, you can run a softmax on it.
print(torch.nn.functional.softmax(output[0], dim=0))
traced = torch.jit.trace(model, input_batch)
sum(p.numel() * p.element_size() for p in traced.parameters())
tf = pathlib.Path('~/Documents/pytorch/data/data/example_debug_map_with_tensorkey.ptl')
torch.jit.save(traced, tf.name)
print(pathlib.Path(tf.name).stat().st_size)
traced._save_for_lite_interpreter(tf.name)
print(pathlib.Path(tf.name).stat().st_size)
print(tf.name)
```
3. Run `python test_lite.py`
```
import torch
from torch.jit.mobile import _load_for_lite_interpreter
# sample execution (requires torchvision)
from PIL import Image
from torchvision import transforms
input_image = Image.open('~/Documents/pytorch/data/dog.jpg')
preprocess = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
input_tensor = preprocess(input_image)
input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model
reload_lite_model = _load_for_lite_interpreter('~/Documents/pytorch/experiment/example_debug_map_with_tensorkey.ptl')
with torch.no_grad():
output_lite = reload_lite_model(input_batch)
# Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
print(output_lite[0])
# The output has unnormalized scores. To get probabilities, you can run a softmax on it.
print(torch.nn.functional.softmax(output_lite[0], dim=0))
```
4. Compare the result with pytorch in master and pytorch built locally with this change, and see the same output.
5. The model size was 16.1 MB and becomes 12.9 with this change.
Size comparison in production models:
{F603127047}
Reviewed By: iseeyuan
Differential Revision: D27759891
fbshipit-source-id: 34e0cb8149011c46c1910165b545c137d7a0b855
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/57705
This will enable module level debug info for benchmarking binary.
Test Plan: Run on AIBench
Reviewed By: larryliu0820
Differential Revision: D28230948
fbshipit-source-id: 5d06c6853d049ff678995a2ed4a86f4e6c85bdc7
Summary:
Add an api `_get_bytecode_version` to get version number given a bytecode model in both cxx and python, and the input can be both from file path and buffer.
## Test
CI (new added unit test will run as part of `pytorch_core-buck`)
1. run test_lite_interpreter.cpp
2. `python test/mobile/test_bytecode.py`
Pull Request resolved: https://github.com/pytorch/pytorch/pull/56801
ghstack-source-id: 128169647
Test Plan:
CI (new added unit test will run as part of `pytorch_core-buck`)
1. run test_lite_interpreter.cpp
2. `python test/mobile/test_bytecode.py`
Reviewed By: iseeyuan
Differential Revision: D27961417
fbshipit-source-id: f786cc9573d855feecff0b4fe8e5363e25f5728c
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/55252
Earlier for bytecode serialization we were saving debug handles only for OPs and not all
instructions. This PR makes changes to add that for all instructions.
Test Plan:
python test/mobile/test_lite_script_module.py TestLiteScriptModule
Imported from OSS
Reviewed By: dreiss
Differential Revision: D27542502
fbshipit-source-id: cff75118c721ce9f0c2f60d2c9471481f05264ca
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/55062
This diff introduces the following changes:
1. InlinedCallStack pickler/serializer is introduced. It is serialized
as a tuple of {module_instance_info, source range tag, callee:InlinedCallStack}
Module instance info is serialized as tuple of {class_type_name,
instance_name}.
Note that callee of the serialized inlined callstack points to the tuple
of already serialized callstack. This means the first callstack ptr to
serialize, will serialize entire path of the tree, where some callee
nodes might be shared with callstack pointers that will be serialized
subsequently. Pickler supports memoization of pickled objects, where if
a tuple has been serialized then object id is obtained instead of
serialized object again. Thus we stll serialize the tree and not every
path from the root separately. Furthermore, InlinedCallStackSerializer
also uses cache to lookup the pointer and return the serialized IValue.
Furthermore, note that we must also serialize the source range of
InlinedCallStack. In order to this serializer requires map of
source-range-tags-to-source-range map. This was done in the previous
diff, where as part of source range serialization we also generate
unique tags. These are the tags that are serialized in InlinedCallStack.
Thus during deserialization we would have to deserialize source range
before deserializing InlinedCallStacks.
2. Furthermore, each serialized InlinedCallStack is serialized with a
unique debug_handle and source range tag.
BackendDebugHandleManager manages generation of
unique debug handles and saves the map of
debug-handles-to-{source_range_tag, inlined-callstack-ptr}.
This map is then serialized as callstack_debug_map.pkl. Note that
inlined callstack is not sufficient to get all the source information
since it contains source information about the nodes which are inlined.
The top-of-the-stack (or bottom) node, which is the actual op node, is
not part of the inlined callstack pointer and thus the source range of
this node is serialized separately using source_range_tag. This is
similar to how JIT creates callstack in
torch/csrc/jit/runtime/interpreter.cpp
Unique debug handles facilitates exception throwing or profiling using
just the debug handle without any further qualifications, such as which
function or module the inlined-callstack belongs to.
Furthermore, this diff refactors the old mobile code for tracking
module hierarchy information per op. Mainly now bytecode serialization
will serialize debug handles corresponding to ops/nodes in graph and
have callstack_debug_map.pkl help generate:
1. Entire callstack and
2. Module hierarchy information.
Test Plan:
python test/mobile/test_lite_script_module.py TestLiteScriptModule
./build/bin/test_jit --gtest_filter=*ModuleInfo
Imported from OSS
Reviewed By: raziel
Differential Revision: D27468709
fbshipit-source-id: 53e2413e7703ead01c77718b7c333c7c6ff50a23
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/54284
In order to bring mobile deployment, via lite interpreter, on feature
parity with JIT, with respect model level debug information we must make
model level debug information available to mobile runtime.
At the moment, model level debug information is stored in SourceRange
which associates node's of graph to where the come from in original
python source code.
This information is serialized as part of debug_pkl and deserialized
when JIT loads the model and reads the model code.
On lite interpreter, we do not have access to all the functionality of
JIT and hence we cannot load model in the same way as JIT, by reading
code, constructing module hierarchy and graph corresponding module
methods etc. Instead in, lite interpreter, only bytecode corresonding to
the compiled graph, Code, is saved.
Thus in order to annotate OPs in the bytecode with equivalent
SourceRange information we do the following:
1. During model serialization, we create a unique tag for each source
range of the model.
2. Create a map of <SourceRange, tag>
3. During debug_pkl serialization we save tag along with SourceRange, on
top of byte offset.
4. During bytecode generation, the methods of the top module are
lowered. During this process methods are inlined. In the inlined graph,
when the node of a graph is lowered to bytecode, we query node's source
range and look it up against the map.
5. Resulting source range tag is serialized in module_debug_info.
6. During model deserialization, we read all the debug_pkl records in
the archieve and create a map of <tag, SourceRange>
7. This map can be used to find source code information.
During mobile runtime:
1. We read all the debug_pkl records and create <tag=debug_handle,
SourceRange> map.
1.1 This map, MobileDebugInfo, is a member of mobile Module.
2. Interpreter catches appropriate exceptions and sets the thread local
debug handle and rethrows the exception.
3. In Function's run method we catch exception and query current debug
handle where the exception happened.
4. Query MobileDebugInfo with debug handle to retrieve source range and
augment error with source range info.
This information is still incomplete as it does not contain entire
callstack.
In the following diffs we will serialize InlinedCallStack directly.
Note that compilation is gated by SYMBOLICATE_MOBILE_DEBUG_HANDLE macro,
so that mobile builds can avoid building MobileDebugInfo, source range
and source range pickler/unpickler. Later we will add path where, if
building without debug support stack trace will contain only debug
handles. They can be symbolicated later.
Test Plan:
Ported bunch of source range tests from test_jit.py. Added on more test
in test_lite_interpreter.py
Imported from OSS
Reviewed By: raziel
Differential Revision: D27174722
fbshipit-source-id: a7b7c6088ce16dec37e823c7fefa4f0b61047e12
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/57098
1. Separate `readArchiveAndTensors()` from `jit/import.cpp` to a new file `jit/import_read.cpp`.
2. Use `readArchiveAndTensors()` in `mobile/import.cpp`
ghstack-source-id: 127703081
3. Add a util function in cpp that could read .pkl files directly instead of loading the entire module
Test Plan: CI
Reviewed By: raziel, iseeyuan
Differential Revision: D28052193
fbshipit-source-id: c8d57f3270bdcf2e52a32f7c111899bd5da7cac2
Summary:
This is an automatic change generated by the following script:
```
#!/usr/bin/env python3
from subprocess import check_output, check_call
import os
def get_compiled_files_list():
import json
with open("build/compile_commands.json") as f:
data = json.load(f)
files = [os.path.relpath(node['file']) for node in data]
for idx, fname in enumerate(files):
if fname.startswith('build/') and fname.endswith('.DEFAULT.cpp'):
files[idx] = fname[len('build/'):-len('.DEFAULT.cpp')]
return files
def run_clang_tidy(fname):
check_call(["python3", "tools/clang_tidy.py", "-c", "build", "-x", fname,"-s"])
changes = check_output(["git", "ls-files", "-m"])
if len(changes) == 0:
return
check_call(["git", "commit","--all", "-m", f"NOLINT stubs for {fname}"])
def main():
git_files = check_output(["git", "ls-files"]).decode("ascii").split("\n")
compiled_files = get_compiled_files_list()
for idx, fname in enumerate(git_files):
if fname not in compiled_files:
continue
if fname.startswith("caffe2/contrib/aten/"):
continue
print(f"[{idx}/{len(git_files)}] Processing {fname}")
run_clang_tidy(fname)
if __name__ == "__main__":
main()
```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/56892
Reviewed By: H-Huang
Differential Revision: D27991944
Pulled By: malfet
fbshipit-source-id: 5415e1eb2c1b34319a4f03024bfaa087007d7179
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/56044
We want to be able to drop the dependence of full-jit deps in the auto-generated unit tests for 2 reasons:
1. Running bloaty on the auto-generated unit tests should be somewhat representative of the actual size.
2. The runtime environment of the auto-generated unit tests should be as close to the production environment as possible to ensure that we are running the tests in a production-like runtime.
Due to the dependece on full-jit, we aren't there yet. For the auto-generated tests, we probably don't need to depend on `_export_operator_list()` evetually, but for now we do since it is used to decide whether the model being run is a Metal GPU model or a CPU model, and gates whether the test runs that model or not.
Eventually, we can stop doing this in the test and do it in the codegen from PTM-CLI instead (by fetching the operators from that tool, and writing out to the BUCK file which backend(s) this model is targeting). However, that will take some time to land, so in the spirit of expediency, this change is being proposed.
Discussed this offline with iseeyuan
ghstack-source-id: 126656877
Test Plan: Build + BSB.
Reviewed By: iseeyuan
Differential Revision: D27694781
fbshipit-source-id: f31a2dfd40803c02f4fd19c45a3cc6fb9bdf9697
Summary:
*Context:* https://github.com/pytorch/pytorch/issues/53406 added a lint for trailing whitespace at the ends of lines. However, in order to pass FB-internal lints, that PR also had to normalize the trailing newlines in four of the files it touched. This PR adds an OSS lint to normalize trailing newlines.
The changes to the following files (made in 54847d0adb9be71be4979cead3d9d4c02160e4cd) are the only manually-written parts of this PR:
- `.github/workflows/lint.yml`
- `mypy-strict.ini`
- `tools/README.md`
- `tools/test/test_trailing_newlines.py`
- `tools/trailing_newlines.py`
I would have liked to make this just a shell one-liner like the other three similar lints, but nothing I could find quite fit the bill. Specifically, all the answers I tried from the following Stack Overflow questions were far too slow (at least a minute and a half to run on this entire repository):
- [How to detect file ends in newline?](https://stackoverflow.com/q/38746)
- [How do I find files that do not end with a newline/linefeed?](https://stackoverflow.com/q/4631068)
- [How to list all files in the Git index without newline at end of file](https://stackoverflow.com/q/27624800)
- [Linux - check if there is an empty line at the end of a file [duplicate]](https://stackoverflow.com/q/34943632)
- [git ensure newline at end of each file](https://stackoverflow.com/q/57770972)
To avoid giving false positives during the few days after this PR is merged, we should probably only merge it after https://github.com/pytorch/pytorch/issues/54967.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/54737
Test Plan:
Running the shell script from the "Ensure correct trailing newlines" step in the `quick-checks` job of `.github/workflows/lint.yml` should print no output and exit in a fraction of a second with a status of 0. That was not the case prior to this PR, as shown by this failing GHA workflow run on an earlier draft of this PR:
- https://github.com/pytorch/pytorch/runs/2197446987?check_suite_focus=true
In contrast, this run (after correcting the trailing newlines in this PR) succeeded:
- https://github.com/pytorch/pytorch/pull/54737/checks?check_run_id=2197553241
To unit-test `tools/trailing_newlines.py` itself (this is run as part of our "Test tools" GitHub Actions workflow):
```
python tools/test/test_trailing_newlines.py
```
Reviewed By: malfet
Differential Revision: D27409736
Pulled By: samestep
fbshipit-source-id: 46f565227046b39f68349bbd5633105b2d2e9b19
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/54428
Using c10::ArrayRef as the parameter type makes the API more flexible and allows the caller to leverage small-buffer optimizations (e.g. c10::SmallVector, std::array) for performance critical cases.
Test Plan: No behavioral changes. Run the existing unit and integration tests.
Reviewed By: suo
Differential Revision: D27232222
fbshipit-source-id: 7b13bc6bd02257097ca119077028fbccc68cc925
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/53677
When serializing bytecode, we serialize it based on methods. It may happen that there are multiple instances of a class. In such a case, the methods inside the class may be serialized multiple times.
To reduce the duplication, we cache the qualified name of the methods, so that one method is serialized only once.
Test Plan: existing unittests and CI
Reviewed By: dhruvbird, raziel
Differential Revision: D26933945
Pulled By: iseeyuan
fbshipit-source-id: 8a9833949fa18f7103a5a0be19e2028040dc7717
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/53410
**Summary**
This commit enables indexing into `ModuleList` using a non-literal
index if the LHS of the assignment statement of which the indexing is
the RHS is annotated with an interface type.
This feature already exists for `ModuleDict`, and this commit builds on
top of that implementation. A `prim::ModuleContainerIndex` operator is
emitted for any statement of the form `lhs: InterfaceType =
module_container[idx]`. The same operator has to be used for both
`ModuleDict` and `ModuleList` because serialization does not preserve
the metadata that indicates whether a `Module` is a `ModuleDict` or
`ModuleList`.
**Testing**
This commit extends the existing unit tests for non-literal `ModuleDict`
indexing to test non-literal `ModuleList` indexing.
**Fixes**
This commit fixes#47496.
Test Plan: Imported from OSS
Reviewed By: gmagogsfm
Differential Revision: D26857597
Pulled By: SplitInfinity
fbshipit-source-id: d56678700a264d79aae3de37ad6b08b080175f7c
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/52333
Export_opnames current documentation is a bit misleading. Change it to better clarify what it does.
ghstack-source-id: 121810264
Test Plan: n/a
Reviewed By: iseeyuan
Differential Revision: D26471803
fbshipit-source-id: 496d10b161c9a4076c4e12db8a0affafc4e1e359
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/51902
These seem like straightforward improvements. (I don't have measurements; feel free to reject if you're skeptical)
ghstack-source-id: 121278775
Test Plan: CI
Reviewed By: qizzzh
Differential Revision: D26322438
fbshipit-source-id: d393a32cc34bb68bc4f804f4b1cc5a8af27763c9
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/51432
ghstack-source-id: 120976584
torchbind is a convenient way to include custom class to both python and torchscript. CREATE_OBJECT is used to create an object of custom class.
CREATE_OBJECT was not supported by lite interpreter. The major reason was that for custom class directly defined in Python, there's no language parser in lite interpreter. It's still the case. However, for torchbind classes that are defined in C++, a python/torchscript parser is not needed.
This diff is to support the case of torchbind custom classes.
1. The class type can be resolved at import level.
2. If the class is not the supported torchbind class, an error message is provided at export stage. Workaround is also suggested.
3. Unit tests. C++: ```LiteInterpreterTest::BuiltinClass``` is added as an end-to-end test on supported class. Python: ```test_unsupported_createobject``` is changed to ```test_unsupported_classtype``` to test unsupported classes.
Test Plan: CI
Reviewed By: raziel
Differential Revision: D26168913
fbshipit-source-id: 74e8b6a12682ad8e9c39afdfd2b605c5f8e65427
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/50229
`fastmod -m 'cast(<((at|c10)::)?\w+Type>\(\)\s*)->' 'castRaw${1}->'` Presuming it builds, this is a safe change: the
result of `cast()` wasn't being saved anywhere, so we didn't need
it, so we can use a raw pointer instead of a new `shared_ptr`.
ghstack-source-id: 120769170
Test Plan: CI
Reviewed By: SplitInfinity
Differential Revision: D25837494
fbshipit-source-id: 46319100dc0dfc78f6d2b45148207f83481f2ada
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/48863
Support default arguments when invoking a module via PyTorch Lite (`mobile::Module`).
Test Plan:
buck test mode/dbg //caffe2/test/cpp/jit:jit -- LiteInterpreterTest.MethodInvocation
buck test mode/dbg caffe2/test:mobile -- test_method_calls_with_optional_arg
Reviewed By: iseeyuan
Differential Revision: D25896212
fbshipit-source-id: 6d7e7fd5f3244a88bd44889024d81ad2e678ffa5
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/50832
Please see the previous diff in this stack for the motivation to do so. This makes the same change but for the non-mobile codebase.
ghstack-source-id: 120184012
Test Plan: Sandcastle + Build
Reviewed By: raziel, iseeyuan
Differential Revision: D25979986
fbshipit-source-id: 7708f4f6a50cb16d7a23651e5655144d277d0a4f
Summary:
Add a new device type 'XPU' ('xpu' for lower case) to PyTorch. Changes are needed for code related to device model and kernel dispatch, e.g. DeviceType, Backend and DispatchKey etc.
https://github.com/pytorch/pytorch/issues/48246
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49786
Reviewed By: mrshenli
Differential Revision: D25893962
Pulled By: ezyang
fbshipit-source-id: 7ff0a316ee34cf0ed6fc7ead08ecdeb7df4b0052
Summary:
Handle sequence output shape and type inference.
This PR fixes value type of sequence outputs. Prior to this, all model sequence type outputs were unfolded for ONNX models.
This PR also enable shape inference for sequence outputs to represent the dynamic shape of these values.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46542
Reviewed By: ezyang
Differential Revision: D24924236
Pulled By: bzinodev
fbshipit-source-id: 506e70a38cfe31069191d7f40fc6375239c6aafe
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/50521
Original commit changeset: 9731ec1e0c1d
Test Plan:
- run `arc focus2 -b pp-ios //xplat/arfx/tracking/segmentation:segmentationApple -a ModelRunner --force-with-bad-commit `
- build via Xcode, run it on an iOS device
- Click "Person Segmentation"
- Crash observed without the diff patched, and the segmentation image is able to be loaded with this diff patched
Reviewed By: husthyc
Differential Revision: D25908493
fbshipit-source-id: eef072a8a3434b932cfd0646ee78159f72be5536
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/50228
`fastmod -m 'expect(<((at|c10)::)?\w+Type>\(\)\s*)->'
'expectRef${1}.'`
Presuming it builds, this is a safe change: the result of `expect()`
wasn't being saved anywhere, so we didn't need it, so we can take a
reference instead of a new `shared_ptr`.
ghstack-source-id: 119782961
Test Plan: CI
Reviewed By: SplitInfinity
Differential Revision: D25837374
fbshipit-source-id: 86757b70b1520e3dbaa141001e7976400cdd3b08
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/49916
Test Plan:
1. Build pytorch locally. `MACOSX_DEPLOYMENT_TARGET=10.9 CC=clang CXX=clang++ USE_CUDA=0 DEBUG=1 MAX_JOBS=16 python setup.py develop`
2. Run `python save_lite.py`
```
import torch
# ~/Documents/pytorch/data/dog.jpg
model = torch.hub.load('pytorch/vision:v0.6.0', 'shufflenet_v2_x1_0', pretrained=True)
model.eval()
# sample execution (requires torchvision)
from PIL import Image
from torchvision import transforms
import pathlib
import tempfile
import torch.utils.mobile_optimizer
input_image = Image.open('~/Documents/pytorch/data/dog.jpg')
preprocess = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
input_tensor = preprocess(input_image)
input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model
# move the input and model to GPU for speed if available
if torch.cuda.is_available():
input_batch = input_batch.to('cuda')
model.to('cuda')
with torch.no_grad():
output = model(input_batch)
# Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
print(output[0])
# The output has unnormalized scores. To get probabilities, you can run a softmax on it.
print(torch.nn.functional.softmax(output[0], dim=0))
traced = torch.jit.trace(model, input_batch)
sum(p.numel() * p.element_size() for p in traced.parameters())
tf = pathlib.Path('~/Documents/pytorch/data/data/example_debug_map_with_tensorkey.ptl')
torch.jit.save(traced, tf.name)
print(pathlib.Path(tf.name).stat().st_size)
traced._save_for_lite_interpreter(tf.name)
print(pathlib.Path(tf.name).stat().st_size)
print(tf.name)
```
3. Run `python test_lite.py`
```
import torch
from torch.jit.mobile import _load_for_lite_interpreter
# sample execution (requires torchvision)
from PIL import Image
from torchvision import transforms
input_image = Image.open('~/Documents/pytorch/data/dog.jpg')
preprocess = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
input_tensor = preprocess(input_image)
input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model
reload_lite_model = _load_for_lite_interpreter('~/Documents/pytorch/experiment/example_debug_map_with_tensorkey.ptl')
with torch.no_grad():
output_lite = reload_lite_model(input_batch)
# Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
print(output_lite[0])
# The output has unnormalized scores. To get probabilities, you can run a softmax on it.
print(torch.nn.functional.softmax(output_lite[0], dim=0))
```
4. Compare the result with pytorch in master and pytorch built locally with this change, and see the same output.
5. The model size was 16.1 MB and becomes 12.9 with this change.
Imported from OSS
Reviewed By: kimishpatel, iseeyuan
Differential Revision: D25731596
Pulled By: cccclai
fbshipit-source-id: 9731ec1e0c1d5dc76cfa374d2ad3d5bb10990cf0
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/48868
Building on the previous diff, we can make `toTensor()` return a
`const Tensor&`, which should make it easier to avoid reference
counting.
ghstack-source-id: 119327372
Test Plan: internal benchmarks.
Reviewed By: bwasti
Differential Revision: D25325379
fbshipit-source-id: ca699632901691bcee432f595f75b0a4416d55dd
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49990
**Summary**
This commit removes the forward-compatibility gate for buffer metadata
serialization. It was introduced to allow versions of fbcode
binaries statically linked against older versions of PyTorch (without
buffer metadata in JIT) to deserialize archives produced by new versions
of PyTorch. Enough time has probably passed that these old binaries
don't exist anymore, so it should be safe to remove the gate.
**Test Plan**
Internal tests.
Test Plan: Imported from OSS
Reviewed By: xw285cornell
Differential Revision: D25743199
Pulled By: SplitInfinity
fbshipit-source-id: 58d82ab4362270b309956826e36c8bf9d620f081
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49385
Currently, the API to export operator lists accepts a `torch::jit::Module` object, and spits out an operator list. The operator list is practically used only for mobile. This is not ideal because the set of root operators may change by the time the model is subsequently optmized and exported for mobile.
What we need to to instead is glean the list of operators from the mobile model itself (`bytecode.pkl` specifically), and expose that instead.
Also updated the logic in `converter`.
### Before this change:
1. Get operator List from Torch Script Model
2. Convert to bytecode mobile model
### After this change:
1. Convert to bytecode mobile model
2. Use this converted mobile model to get the list of operators for each method on the model
ghstack-source-id: 118796752
Test Plan:
Added a unit test in `test_lite_interpreter.cpp` to ensure that all model referenced operators show up in the exported operator list. Also make `test_lite_interpreter.cpp` runnable from `xplat/caffe2/BUCK` since this is where the production code will be built from.
Verified that the list of operators produced before and after this change for an example model (segmentation) are the same.
{P147863234}
Also verified that the operator lists for BI-Xray model is different (we have been having problems with missing operators for this one): {P154903132}
Reviewed By: iseeyuan
Differential Revision: D24690094
fbshipit-source-id: 0426a6ef90456a811010cfe337c415882ae2deff
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/48863
Support default arguments when invoking a module via PyTorch Lite (`mobile::Module`).
Test Plan:
buck test mode/dbg //caffe2/test/cpp/jit:jit -- LiteInterpreterTest.MethodInvocation
buck test mode/dbg caffe2/test:mobile -- test_method_calls_with_optional_arg
Reviewed By: raziel, iseeyuan
Differential Revision: D25152559
fbshipit-source-id: bbf52f1fbdbfbc6f8fa8b65ab524b1cd4648f9c0
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49146
Add support for Storage arguments to IValue and the JIT typing system, and make ops that were blocked on that c10-full.
ghstack-source-id: 118710665
(Note: this ignores all push blocking failures!)
Test Plan: waitforsandcastle
Reviewed By: ezyang
Differential Revision: D25456799
fbshipit-source-id: da14f125af352de5fcf05a83a69ad5a69d5a3b45
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/48802
Current torch::jit::load API only supports unique_ptr ReadAdaptInterface input, but for some cases, torch::jit::load may not be the only consumer of the reader adapter. This diff enables an overload of torch::jit::load to load shared_ptr PyTorchStreamReader.
Reviewed By: malfet, houseroad
Differential Revision: D25241904
fbshipit-source-id: aa403bac9ed820cc0e94342aebfe524a1d5bf913
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46827
TensorPipe RPC agent uses JIT pickler/unpickler to serialize/deserialize
tensors. Instead of saving tensors to a file, the agent can directly
invoke `cudaMemcpy` to copy tensors from the sender to the receiver
before calling into JIT unpickler. As a result, before unpickling,
the agent might already have allocated tensors and need to pass
them to the JIT unpickler. Currently, this is done by providing a
`read_record` lambda to unpickler for CPU tensors, but this is
no longer sufficient for zero-copy CUDA tensors, as the unpickler
always allocate the tensor on CPU.
To address the above problem, this commit introduces a `use_storage_device`
flag to unpickler ctor. When this flag is set, the unpickler will
use the device from the `DataPtr` returned by the `read_record`
lambda to override the pickled device information and therefore
achieves zero-copy.
Test Plan: Imported from OSS
Reviewed By: wanchaol
Differential Revision: D24533218
Pulled By: mrshenli
fbshipit-source-id: 35acd33fcfb11b1c724f855048cfd7b2991f8903
Summary:
Pull Request resolved: https://github.com/pytorch/glow/pull/5062
Pull Request resolved: https://github.com/pytorch/pytorch/pull/45556
User defined classes can be used as constants. This is useful when freezing and removing the module from the graph.
Test Plan: waitforsadcastle
Reviewed By: eellison
Differential Revision: D23994974
fbshipit-source-id: 5b4a5c91158aa7f22df39d71f2658afce1d29317
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/47775
When serializing graphs, we check every node for named types referenced,
so that we can register them as dependencies. We were skipping this
check for the graph inputs themselves. Since types used at input are
almost always used somewhere in the graph, we never noticed this gap
until a user reported an issue with NamedTuples.
Test Plan: Imported from OSS
Reviewed By: jamesr66a
Differential Revision: D24896289
Pulled By: suo
fbshipit-source-id: 4ce76816cb7997a7b65e7cea152ea52ed8f27276
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/45716
**Summary**
This commit enables indexing into `ModuleDict` using a non-literal
index if the `ModuleDict` is annotated with `Dict[str, X]`, where `X` is
a module interface type. These annotations must be expressed using a
class attribute named `__annotations__`, which is a `Dict[str, Type]`
where the keys are the names of module attributes and the values are
their types.
The approach taken by this commit is that these annotations are stored
as "hints" along with the corresponding module attributes in the
`ConcreteSubmoduleTypeBuilder` instance for each module (which might be
a `ModuleDict`). These hints are passed into the `ModuleValue` that is
created for desugaring operations on submodules so that indexing into a
`ModuleDict` can be emitted as a getitem op into a dict emitted into the
graph that represents the `ModuleDict`.
**Test Plan**
This commit adds unit tests to `TestModuleContainers` to test this
feature (`test_typed_module_dict`).
Differential Revision: D24070606
Test Plan: Imported from OSS
Reviewed By: ansley
Pulled By: SplitInfinity
fbshipit-source-id: 6019a7242d53d68fbfc1aa5a49df6cfc0507b992
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46686
I was trying to page this code back in after a while and some things
stuck out as unnecessarily confusing.
1. Improve documentation of closures and fork stuff to be more accurate
to how we use them today.
2. Change `prim::LocalVariableScope` to `prim::ListComprehension`. It is
only ever used for a list comprehensions, and in general the nodes
emitted by `ir_emitter` should correspond to concrete operations or
language features rather than semantic constraints.
3. Change the somewhat mysterious "inputs" and "attributes" argument
names throughout the codebase to be the more obvious "args" and "kwargs"
that they generally represent (I think "inputs" and "attributes" come
from the AST naming).
Test Plan: Imported from OSS
Reviewed By: navahgar, jamesr66a
Differential Revision: D24464197
Pulled By: suo
fbshipit-source-id: 1f4b1475b58b5690a0b204e705caceff969533b4
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46543
Add error messages and workaround for RET failure of containers with a torch class type.
- Error case condition
1) ins.op == RET
2) input_type == TypeKind::ListType or TypeKind::DictType
3) Any(input_type's element type) == TypeKind::ClassType
ghstack-source-id: 114618426
Test Plan:
buck test mode/dev caffe2/test:mobile -- 'test'
Summary
Pass: 13
ListingSuccess: 1
Finished test run: https://our.intern.facebook.com/intern/testinfra/testrun/7318349417617713
Reviewed By: iseeyuan
Differential Revision: D24388483
fbshipit-source-id: 7d30f6684a999054d0163e691422797cb818bb6a
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46347
Added the named tuple's error messages & workarounds when it returns from a function of a class in Pytorch Mobile.
To identify the error cases (returning NamedTuple type), I used the following coditions:
1) ins.op == RET (for returing)
2) type->kind() == TypeKind::TupleType (for pruning non-tuple types)
3) type->cast<TupleType>().name() (for pruning Tuple type)
- I could use the type's str (str() or repr_str()) directly, but I used whether it has the "name" attribute. Please give the comment for this.
[Information of Tuple and NamedTuple types]
1. Tuple
type->str(): (int, int)
type->repr_str(): Tuple[int, int]
type->kind(): TypeKind::TupleType # different with other types
type()->cast<NamedType>(): True
type()->cast<NamedType>()>name(): False # different with NamedTuple
2. NamedTuple
type->str(): __torch__.myNamedTuple
type->repr_str(): __torch__.myNamedTuple
type->kind(): TypeKind::TupleType # different with other types
type()->cast<NamedType>(): True
type->cast<TupleType>().name() = True # different with Tuple
(From the next diff, I will handle the other error cases: 1) returning List<module class>, Dict<module class> and 2) accessing Module class's member functions)
ghstack-source-id: 114361762
Test Plan:
[Added test results]
buck test mode/dev caffe2/test:mobile -- 'test_unsupported_return'
Summary
Pass: 2
ListingSuccess: 1
Finished test run: https://our.intern.facebook.com/intern/testinfra/testrun/7036874440497926
[Whole test results]
buck test mode/dev caffe2/test:mobile -- 'test'
Summary
Pass: 11
ListingSuccess: 1
Finished test run: https://our.intern.facebook.com/intern/testinfra/testrun/4503599664074084
Reviewed By: iseeyuan
Differential Revision: D24291962
fbshipit-source-id: a1a9e24e41a5f1e067738f59f1eae34d07cba31a
Summary:
The record_stream method was hard coded for CUDA device. Define the record_stream in the native_functions.yaml to enable the dynamic dispatch to different end device.
Fixes https://github.com/pytorch/pytorch/issues/36556
Pull Request resolved: https://github.com/pytorch/pytorch/pull/44301
Reviewed By: glaringlee
Differential Revision: D23763954
Pulled By: ezyang
fbshipit-source-id: e6d24f5e7892b56101fa858a6cad2abc5cdc4293
Summary:
* Support propagating `dim_param` in ONNX by encoding as `ShapeSymbol` in `SymbolicShape` of outputs. If export is called with `dynamic_axes` provided, shape inference will start with these axes set as dynamic.
* Add new test file `test_pytorch_onnx_shape_inference.py`, reusing all test cases from `test_pytorch_onnx_onnxruntime.py`, but focus on validating shape for all nodes in graph. Currently this is not enabled in the CI, since there are still quite some existing issues and corner cases to fix. The test is default to run only at opset 12.
* Bug fixes, such as div, _len, and peephole.cpp passes for PackPadded, and LogSoftmaxCrossEntropy.
* This PR depends on existing PR such as 44332.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/44920
Reviewed By: eellison
Differential Revision: D23958398
Pulled By: bzinodev
fbshipit-source-id: 00479d9bd19c867d526769a15ba97ec16d56e51d
Summary:
Optimize export_onnx api to reduce string and model proto exchange in export.cpp
Pull Request resolved: https://github.com/pytorch/pytorch/pull/44332
Reviewed By: bwasti, eellison
Differential Revision: D23880129
Pulled By: bzinodev
fbshipit-source-id: 1d216d8f710f356cbba2334fb21ea15a89dd16fa
Summary:
Previously, `prim::EnumValue` is serialized to `ops.prim.EnumValue`, which doesn't have the right implementation to refine return type. This diff correctly serializes it to enum.value, thus fixing the issue.
Fixes https://github.com/pytorch/pytorch/issues/44892
Pull Request resolved: https://github.com/pytorch/pytorch/pull/44891
Reviewed By: malfet
Differential Revision: D23818962
Pulled By: gmagogsfm
fbshipit-source-id: 6edfdf9c4b932176b08abc69284a916cab10081b
Summary:
There's an annoying O(N^2) in module export logic that makes saving some of the models (if they have many classes) take eternity.
I'm not super familiar with this code to properly untangle the deps and make it a pure hash lookup. So I just added a side lookup table for raw pointers. It's still quadratic, but it's O(num_classes^2) instead of O(num_classes * num_references) which already gives huge savings.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/44589
Test Plan:
Tested with one of the offending models - just loading a saving a Torchscript file:
```
Before:
load 1.9239683151245117
save 165.74712467193604
After:
load 1.9409027099609375
save 1.4711427688598633
```
Reviewed By: suo
Differential Revision: D23675278
Pulled By: dzhulgakov
fbshipit-source-id: 8f3fa7730941085ea20d9255b49a149ac1bf64fe
Summary:
* Support sequence type (de)serialization, enables onnx shape inference on sequence nodes.
* Fix shape inference with block input/output: e.g. Loop and If nodes.
* Fix bugs in symbolic discovered by coverage of onnx shape inference.
* Improve debuggability: added more jit logs. For simplicity, the default log level, when jit log is enabled, will not dump ir graphs.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/43929
Reviewed By: albanD
Differential Revision: D23674604
Pulled By: bzinodev
fbshipit-source-id: ab6aacb16d0e3b9a4708845bce27c6d65e567ba7
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/43043
This add the support for rpc_sync in TorchScript in a way similar to
rpc_async
Test Plan: Imported from OSS
Reviewed By: mrshenli
Differential Revision: D23252039
Pulled By: wanchaol
fbshipit-source-id: 8a05329cb8a24079b2863178b73087d47273914c
Summary:
It is often that the conversion from torch operator to onnx operator requires input rank/dtype/shape to be known. Previously, the conversion depends on tracer to provide these info, leaving a gap in conversion of scripted modules.
We are extending the export with support from onnx shape inference. If enabled, onnx shape inference will be called whenever an onnx node is created. This is the first PR introducing the initial look of the feature. More and more cases will be supported following this PR.
* Added pass to run onnx shape inference on a given node. The node has to have namespace `onnx`.
* Moved helper functions from `export.cpp` to a common place for re-use.
* This feature is currently experimental, and can be turned on through flag `onnx_shape_inference` in internal api `torch.onnx._export`.
* Currently skipping ONNX Sequence ops, If/Loop and ConstantOfShape due to limitations. Support will be added in the future.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/40628
Reviewed By: mrshenli
Differential Revision: D22709746
Pulled By: bzinodev
fbshipit-source-id: b52aeeae00667e66e0b0c1144022f7af9a8b2948
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/43584
1. add `metadata.pkl` to `.bc` file which includes the model info that we are interested in
2. load `metadata.pkl` as a attribute `unordered_map<string, string>` in the module
ghstack-source-id: 110730013
Test Plan:
- CI
```buck build //xplat/caffe2:jit_module_saving
```
```buck build //xplat/caffe2:torch_mobile_core
```
Reviewed By: xcheng16
Differential Revision: D23330080
fbshipit-source-id: 5d65bd730b4b566730930d3754fa1bf16aa3957e
Summary:
Original commit changeset: f368d00f7bae
Back out "[2/3][lite interpreter] add metadata when saving and loading models for mobile"
D23047144 (e37f871e87)
Pull Request: https://github.com/pytorch/pytorch/pull/43516
(Note: this ignores all push blocking failures!)
Test Plan: CI
Reviewed By: xcheng16
Differential Revision: D23304639
fbshipit-source-id: 970ca3438c1858f8656cbcf831ffee2c4a551110
Summary:
1. add `metadata.pkl` to `.bc` file which includes the model info that we are interested in
2. load `metadata.pkl` as a attribute `unordered_map<string, string>` in the module
Test Plan:
- CI
```buck build //xplat/caffe2:jit_module_saving
```
```buck build //xplat/caffe2:torch_mobile_core
```
Reviewed By: xcheng16
Differential Revision: D23047144
fbshipit-source-id: f368d00f7baef2d3d15f89473cdb146467aa1e0b
Summary:
[Re-review tips: nothing changed other than a type in python_ir.cpp to fix a windows build failure]
Adds code printing for enum type
Enhance enum type to include all contained enum names and values
Adds code parsing for enum type in deserialization
Enabled serialization/deserialization test in most TestCases. (With a few dangling issues to be addressed in later PRs to avoid this PR grows too large)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/43460
Reviewed By: albanD
Differential Revision: D23284929
Pulled By: gmagogsfm
fbshipit-source-id: e3e81d6106f18b7337ac3ff5cd1eeaff854904f3
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/42963
* Adds code printing for enum type
* Enhance enum type to include all contained enum names and values
* Adds code parsing for enum type in deserialization
* Enabled serialization/deserialization test in most TestCases. (With a few dangling issues to be addressed in later PRs to avoid this PR grows too large)
Test Plan: Imported from OSS
Reviewed By: SplitInfinity
Differential Revision: D23223281
Pulled By: gmagogsfm
fbshipit-source-id: 716d1866b7770dfb7bd8515548cfe7dc4c4585f7
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/43088
Create quantized module that the user can use to perform embedding bag quantization
The module uses the EmbeddingPackedParams to store the weights which can be serialized /deserialized
using TorchBind custom classes (C++ get/setstate code)
Following PR will add support for `from_float` to convert from float to quantized module
Test Plan:
python test/test_quantization.py TestDynamicQuantizedModule.test_embedding_bag_api
Imported from OSS
Reviewed By: vkuzo
Differential Revision: D23167519
fbshipit-source-id: 029d7bb44debf78c4ef08bfebf267580ed94d033
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/42389
**Summary**
This commit adds support for properties to TorchScript classes,
specifically for getters and setters. They are implemented essentially
as pointers to the methods that the corresponding decorators decorate,
which are treated like regular class methods. Deleters for properties
are considered to be out of scope (and probably useless for TorchScript
anyway).
**Test Plan**
This commit adds a unit test for a class with a property that has both
getter and setter and one that has only a getter.
`python test/test_jit.py TestClassType.test_properties`
Test Plan: Imported from OSS
Reviewed By: eellison, ppwwyyxx
Differential Revision: D22880232
Pulled By: SplitInfinity
fbshipit-source-id: 4828640f4234cb3b0d4f3da4872a75fbf519e5b0
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/42133
Test Plan:
We save a module with module debugging information as follows.
```
import torch
m = torch.jit.load('./detect.pt')
# Save module without debug info
m._save_for_lite_interpreter('./detect.bc')
# Save module with debug info
m._save_for_lite_interpreter('./detect.bc', _save_debug_info_in_bytecode=True)
```
Size of the file without module debugging information: 4.508 MB
Size of the file with module debugging information: 4.512 MB
Reviewed By: kimishpatel
Differential Revision: D22803740
Pulled By: taivu1998
fbshipit-source-id: c82ea62498fde36a1cfc5b073e2cea510d3b7edb
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/40719
This is a follow up patch to turn on this feature in order to handle breaking
forward compatibility.
Test Plan: Imported from OSS
Reviewed By: suo
Differential Revision: D22457952
Pulled By: bzinodev
fbshipit-source-id: fac0dfed8b8b5fa2d52d342ee8cf06742959b3c5
Summary:
* Add EnumType and AnyEnumType as first-class jit type
* Add Enum-typed IValue
* Enhanced aten::eq to support Enum
Supported:
Enum-typed function targuments
using Enum type and comparing them
TODO:
Add PyThon sugared value for Enum
Support getting name/value attrs of enums
Support Enum-typed return values
Support enum values of different types in same Enum class
Support serialization and deserialization
Pull Request resolved: https://github.com/pytorch/pytorch/pull/41390
Reviewed By: eellison
Differential Revision: D22524388
Pulled By: gmagogsfm
fbshipit-source-id: 1627154a64e752d8457cd53270f3d14aea4b1150
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/40718
Currently only constant except tensor must be inlined during serialization.
Tensor are stored in the contant table. This patch generalizes this capability
to any IValue. This is particularly useful for non ASCII string literal that
cannot be inlined.
Test Plan: Imported from OSS
Differential Revision: D22298169
Pulled By: bzinodev
fbshipit-source-id: 88cc59af9cc45e426ca8002175593b9e431f4bac
