Recently we made it possible to serialize ExportedPrograms with fake parameters/buffers/etc.
The serialization regime was kind of whacky; basically we serialized a stub and reassembled the FakeTensor using metadata that we had stashed elsewhere in the Graph state.
This was bad for a few reasons:
- Storing the metadata separately from the actual serialized object caused situations where you could have one but not the other. An example case is if you had a FakeTensor contained inside a TorchBind object—there was no obviously place to store the metadata for this. This actually happens—TensorQueue in fbgemm does this.
- It created an annoying cycle: we had to deserialize the Graph's tensor metadata in order to deserialize (potentially faked) constants, but we need constants in order to deserialize the Graph.
This fixes all that. The basic idea is to patch the reducer function for FakeTensor at serialization time, and serialize a copy of the FakeTensor metadata. We already are policing BC for the TensorMeta schema struct so it's not a net increase in the BC surface.
As a bonus, I fixed a weird bug with torchbind tracing where we were accidentally reinterpreting a torch.ScriptObject as a torch.ScriptModule (which was the root cause of some weird behavior @bahuang was seeing last week).
Differential Revision: [D53601251](https://our.internmc.facebook.com/intern/diff/D53601251/)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/119531
Approved by: https://github.com/zhxchen17
Summary:
GraphFunction internally stores the optimized graph after generating it and then it is passed into the executor which makes a copy of it. So we store the optimized graph effectively twice.
This diff allows to set a flag to not store the optimized graph inside the GraphFunction.
The code is NoP right now until the flag is enabled.
Test Plan:
I ran SL with this on raas with good memory saving on raas server. From command line:
exmaple model run
```
buck run mode/opt-clang sigrid/predictor/client/localnet:run_model -- --model_id_to_load=953556500 --model_snapshot_to_load=362
I1207 11:04:58.657143 3556226 SigridPredictorLocalModelFactory.cpp:32] Memory usage for 953556500_362 is 255646 Kb
```
then with flag enabled:
```
buck run mode/opt-clang sigrid/predictor/client/localnet:run_model -- --model_id_to_load=953556500 --model_snapshot_to_load=362 --torch_jit_do_not_store_optimized_graph=true
I1207 11:06:25.245779 3577383 SigridPredictorLocalModelFactory.cpp:32] Memory usage for 953556500_362 is 165167 Kb
```
So collective with this flag and the flag from D51950418
```
buck run mode/opt-clang sigrid/predictor/client/localnet:run_model -- --model_id_to_load=953556500 --model_snapshot_to_load=362 --torch_jit_do_not_store_optimized_graph=true --torch_jit_enable_profiling_graph_executor=false
I1207 11:09:17.502743 3592345 SigridPredictorLocalModelFactory.cpp:32] Memory usage for 953556500_362 is 114848 Kb
```
Differential Revision: D51931895
Pull Request resolved: https://github.com/pytorch/pytorch/pull/115381
Approved by: https://github.com/malfet
Summary: Registering param/buffer will write into a vector inside Object, need to maintain thread safety if we have threads reading from the vector and writing to the vector at the same time.
Test Plan: CI
Differential Revision: D49882601
Pull Request resolved: https://github.com/pytorch/pytorch/pull/110488
Approved by: https://github.com/davidberard98
In almost all cases this is only included for writing the output formatter, which
only uses `std::ostream` so including `<ostream>` is sufficient.
The istream header is ~1000 lines so the difference is non-trivial.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/106914
Approved by: https://github.com/lezcano
In almost all cases this is only included for writing the output formatter, which
only uses `std::ostream` so including `<ostream>` is sufficient.
The istream header is ~1000 lines so the difference is non-trivial.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/106914
Approved by: https://github.com/lezcano
Summary:
Before we copy a meta merge, and use it as a skeleton to do d2d merge replication. However some models like prospector has CPU op LongIndex which takes quite long time to load. That makes the meta merge copy expensive.
Modify jit::Module::deepcopy() to allow device copy. It simplifies user code and removes all unnecessary copies like tempfile, meta merge
Pull Request resolved: https://github.com/pytorch/pytorch/pull/106521
Approved by: https://github.com/davidberard98
As we live in C++17 world
This is a functional no-op, just
- `s/namespace at { namespace native {/namespace at::native {/`
- `s/namespace torch { namespace jit {/namespace torch::jit {/`
Pull Request resolved: https://github.com/pytorch/pytorch/pull/92100
Approved by: https://github.com/izaitsevfb
Apply clang-tidy fixups to prefer member initializer and modernize-pass-by-value. This is a mostly a noop, but it should make a few ctors slighlty more readable and more efficient. Also drops in some missing moves that prevents a lot of unnecessary copying.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/91538
Approved by: https://github.com/ezyang
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74353
Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes:
* Register fake source of generated methods in linecache so that inspect.get_source will succeed.
* this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in.
## Original Summary:
Fixes https://github.com/pytorch/pytorch/issues/72901.
Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this.
What's supported
Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator
Default values for fields
__post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+
Overriding __eq__ or any of the comparison magic methods to provide your own implementation
What's not supported
Default factory initializers for fields
Frozen dataclasses
InitVar on Python 3.7
__repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them)
Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74889
Test Plan:
unittest
Also run previously failed test:
```
buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)'
```
passes
Reviewed By: zhxchen17
Differential Revision: D35206262
Pulled By: qihqi
Pull Request resolved: https://github.com/pytorch/pytorch/pull/76771
Approved by: https://github.com/seemethere
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74353
Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes:
* Register fake source of generated methods in linecache so that inspect.get_source will succeed.
* this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in.
## Original Summary:
Fixes#72901.
Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this.
What's supported
Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator
Default values for fields
__post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+
Overriding __eq__ or any of the comparison magic methods to provide your own implementation
What's not supported
Default factory initializers for fields
Frozen dataclasses
InitVar on Python 3.7
__repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them)
Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment.
Test Plan:
unittest
Also run previously failed test:
```
buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)'
```
passes
Differential Revision: D35206262
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74889
Approved by: https://github.com/zhxchen17
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74186
Make the execution settings mutable on function_impl so that we can set it for running op decompositions. Add mapping to function objects and show example in test of executing op decompositions.
Test Plan: Imported from OSS
Reviewed By: gchanan
Differential Revision: D34938125
Pulled By: eellison
fbshipit-source-id: adf108b2f6c1bd166910c6d7b94245661d67ce0d
(cherry picked from commit 9957e33803002d9e71abe4ff802769270b6960d3)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74012
This allows setting an executor on a function. The first use case is use to decompositions in C++ without additional fusion passes etc which might not work with custom tensors like batched tensors/vmap. A subsequent use case might be taking advantage of invokees of JIT execution which guard on certain properties before invocation (such as complete shapes in AOT autograd, rank in lazy tensor).
Test Plan: Imported from OSS
Reviewed By: gchanan
Differential Revision: D34938124
Pulled By: eellison
fbshipit-source-id: cf7a45416457942b872322cab47d871a8336bdb5
(cherry picked from commit 9c600eb9ad0f2173f003e511268e97584edae36d)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73875
Previously we had a few settings:
- getExecutor - which toggled between Profiling Executor and Legacy
- getGraphOptimize - if true, overrides PE/Legacy to run with simple executor (no optimizations)
and then...
- getProfilingMode - which would set PE to 0 specializtions.
The last mode is redundant with getGraphOptimize, we should just remove it and use getGraphOptimize in these cases. It would lead to potentially invalid combinations of logic - what does mean if getProfilingMode is true but getExecutor is set to false ? This would lead to a bug in specialize_autograd_zero in this case, see: https://github.com/pytorch/pytorch/blob/master/torch%2Fcsrc%2Fjit%2Fpasses%2Fspecialize_autogradzero.cpp#L93.
The tests here are failing but get fixed with the PR above it, so i'll squash for landing.
Test Plan: Imported from OSS
Reviewed By: cpuhrsch
Differential Revision: D34938130
Pulled By: eellison
fbshipit-source-id: 1a9c0ae7f6d1cfddc2ed3499a5af611053ae5e1b
(cherry picked from commit cf69ce3d155ba7d334022c42fb2cee54bb088c23)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74594
Extending `_save_for_mobile` and `_load_for_mobile` to support faltbuffer format with additional optional argument which is set to pick pickle by default.
Adding new binary target with suffix `_pickle_and_flatbuffer` to help migration.
Size test in D34909502 shows the size has regressed by ~40K but after removing pickle and comparing lite_predictors we have ~120K size measure that we will achieve when deprecating pickle and moving to flatbuffer
**BEFORE:**
```lang=mermaid
graph TD;
torch_core-->torch_mobile_deserialize;
torch_mobile_core-->torch_mobile_deserialize;
jit_module_saving-->torch_core;
jit_module_saving-->torch_mobile_core;
torch_mobile_deserialize-->caffe2_serialize;
torch_mobile_deserialize-->torch_mobile_module;
caffe2_serialize-->miniz;
flatbuffer_loader-->mobile_bytecode;
flatbuffer_serializer-->mobile_bytecode;
mobile_bytecode-->flatbuffer_2.0;
flatbuffer_loader-->torch_mobile_module;
flatbuffer_serializer-->torch_mobile_module;
```
**AFTER:**
```lang=mermaid
graph TD;
torch_core-->torch_mobile_deserialize;
torch_mobile_core-->torch_mobile_deserialize;
jit_module_saving-->torch_core;
jit_module_saving-->torch_mobile_core;
torch_mobile_deserialize-->caffe2_serialize;
torch_mobile_deserialize-->torch_mobile_module;
caffe2_serialize-->miniz;
flatbuffer_loader-->mobile_bytecode;
flatbuffer_serializer-->mobile_bytecode;
mobile_bytecode-->flatbuffer_2.0;
torch_mobile_deserialize_pickle_and_flatbuffer-->|new| flatbuffer_loader;
torch_mobile_deserialize_pickle_and_flatbuffer-->|new| torch_mobile_deserialize;
torch_mobile_core_pickle_and_flatbuffer-->|new| torch_mobile_deserialize_pickle_and_flatbuffer;
torch_core_pickle_and_flatbuffer-->|new| torch_mobile_deserialize_pickle_and_flatbuffer;
jit_module_saving_pickle_and_flatbuffer-->|new| torch_core_pickle_and_flatbuffer;
jit_module_saving_pickle_and_flatbuffer-->|new| torch_mobile_core_pickle_and_flatbuffer;
flatbuffer_serializer-->torch_mobile_module;
jit_module_saving_pickle_and_flatbuffer-->|new|jit_module_saving;
jit_module_saving_pickle_and_flatbuffer-->|new|flatbuffer_serializer;
flatbuffer_loader-->torch_mobile_module;
```
Original commit changeset: 780dfb6fd6ba
Original Phabricator Diff: D34805092 (284b2b7135)
ghstack-source-id: 152044801
(Note: this ignores all push blocking failures!)
Test Plan:
CI
```
~/fbsource/fbcode] cd ~/fbsource/fbcode/ && buck test -c fbcode.caffe2_enable_flatbuffer=1 //caffe2/test/cpp/jit:jit -- FlatbufferTest.ExtraFiles
Parsing buck files: finished in 0.9 sec
Building: finished in 5.3 sec (100%) 12992/54304 jobs, 0/54304 updated
Total time: 6.2 sec
More details at https://www.internalfb.com/intern/buck/build/2b387fff-f813-4cfa-b53f-eb2378630d4e
BUILD SUCCEEDED
Tpx test run coordinator for Facebook. See https://fburl.com/tpx for details.
Running with tpx session id: f93a84d6-e7ce-41a0-a97f-0ef3fa6d199d
Trace available for this run at /tmp/tpx-20220323-134108.766518-f93a84d6-e7ce-41a0-a97f-0ef3fa6d199d/trace.log
RemoteExecution session id: reSessionID-f93a84d6-e7ce-41a0-a97f-0ef3fa6d199d-tpx
Started reporting to test run: https://www.internalfb.com/intern/testinfra/testrun/4503599723101693
✓ ListingSuccess: caffe2/test/cpp/jit:jit : 486 tests discovered (19.122)
✓ Pass: caffe2/test/cpp/jit:jit - FlatbufferTest.ExtraFiles (0.187)
Summary
Pass: 1
ListingSuccess: 1
If you need help understanding your runs, please follow the wiki: https://fburl.com/posting_in_tpx_users
Finished test run: https://www.internalfb.com/intern/testinfra/testrun/4503599723101693
```
Similar Build Deps Dags
```
[pavithran@devvm5216.vll0 /data/users/pavithran/fbsource] buck query 'allpaths(//xplat/caffe2:torch_mobile_all_ops_pickle_and_flatbuffer, //xplat/caffe2:torch_mobile_deserialize_pickle_and_flatbuffer)' --output-format dot-compact | pastry
P486770901: https://www.internalfb.com/intern/paste/P486770901/
[pavithran@devvm5216.vll0 /data/users/pavithran/fbsource] buck query 'allpaths(//xplat/caffe2:torch_mobile_all_ops, //xplat/caffe2:torch_mobile_deserialize)' --output-format dot-compact | pastry
P486771278: https://www.internalfb.com/intern/paste/P486771278/
```
pickle_and_flatbuffer: https://www.internalfb.com/intern/dgw/graph/?build_id=P486770901
pickle: https://www.internalfb.com/intern/dgw/graph/?build_id=P486771278
Reviewed By: iseeyuan
Differential Revision: D35067157
fbshipit-source-id: 9044259c17a2e0da79bd6aedb28efbdfd57e23e0
(cherry picked from commit f738069ec3a72e79da56172741d027de514e9e5f)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/72638
All of the other user-facing apis are in this header, this should be too.
Test Plan: Imported from OSS
Reviewed By: malfet
Differential Revision: D34159122
Pulled By: eellison
fbshipit-source-id: 71110ad5543246d0fa822c426ad1cf2f65e017f6
(cherry picked from commit f1862b32e1)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/71778
This assert was broken (never triggers). Fixing the assert leads to test failures. We need to fix those test failures, so a FIXME has been filed. The urgency is avoiding the compile time failure that will come with enabling `-Wstring-conversion` as an error.
Test Plan: CI Pass
Reviewed By: r-barnes
Differential Revision: D33754171
fbshipit-source-id: 834b070b94007af583d0fc6c022f23b6703f3fbc
(cherry picked from commit ac8f905fb1)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/68691
TraceType is a sharded file, so by only including specific operator
headers, we ensure that changing one (non-method) operator only needs
one shard to be re-compiled.
This also changes all the included autograd and jit headers from
including `ATen/ATen.h` to just including `ATen/core/Tensor.h`.
Test Plan: Imported from OSS
Reviewed By: gchanan
Differential Revision: D33336948
Pulled By: albanD
fbshipit-source-id: 4e40371592b9a5a7e7fcd1d8cecae11ffb873113
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/69406
Most files that include `interned_strings.h` don't actually depend on
anything generated from `FORALL_NS_SYMBOLS` yet because they're in a
single file you need to recompile whenever a new symbol is added. Here
I move the class definition into a separate file so this doesn't
happen.
Test Plan: Imported from OSS
Reviewed By: zou3519
Differential Revision: D32923637
Pulled By: albanD
fbshipit-source-id: 6e488cbfcfe2c041a99d9ff22e167dbddf3f46d7
