Commit Graph

19 Commits

Author SHA1 Message Date
bd573389f6 [Bootcamp]Add option for flatbuffer loader to copy memory to individual tensors (#76986)
Summary: Add option for flatbuffer loader to copy memory to individual tensors to allow free memeory without waiting for all tensor runs completed.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/76986
Approved by: https://github.com/qihqi
2022-05-09 17:29:30 +00:00
7d5c07830d Add upgrader related logic to flatbuffer (#71451)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/71451

title

Test Plan: unittest

Reviewed By: tugsbayasgalan

Differential Revision: D33593056

fbshipit-source-id: c48d6ad50e6e2f757b68525dfe07693711b95840
(cherry picked from commit 8e09e20c1dafcdbdb45c2d1574da68a32e54a3a5)
2022-04-17 18:51:23 +00:00
fe8eff3711 Revert "Add upgrader related logic to flatbuffer"
This reverts commit dfae96171a2cc122fe197028fa3b2668998bd2a1.
2022-04-17 11:38:59 -07:00
dfae96171a Add upgrader related logic to flatbuffer
Summary: title

Test Plan: unittest

Differential Revision: D33593056

Pull Request resolved: https://github.com/pytorch/pytorch/pull/71451
Approved by: https://github.com/tugsbayasgalan
2022-04-16 02:04:48 +00:00
6402e62454 Refractor flatbuffer jit code
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75239

Refractor flatbuffer_serializer to move JIT related code to a separate file .

Differential Revision: [D35301020](https://our.internmc.facebook.com/intern/diff/D35301020/)

**NOTE FOR REVIEWERS**: This PR has internal Facebook specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D35301020/)!

Approved by: https://github.com/iseeyuan
2022-04-11 23:41:48 +00:00
3001bda304 [PyTorchEdge] Backport from v9 flatbuffer to v8 pickle (#75201)
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)
2022-04-07 19:43:57 +00:00
f984e50f39 Extend jit::load to work on flatbuffer file; Take 2 (#75256)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75256

ghstack-source-id: 153138970

Test Plan: CI

Reviewed By: iseeyuan

Differential Revision: D35399581

fbshipit-source-id: dafe9d301009d3f70986ed92bfe06d160ab90ba0
(cherry picked from commit ccc860fd07946de5aae12bc179a0b8bbba83b997)
2022-04-06 17:54:01 +00:00
32e58c73c4 Back out "Extend jit::load to work on flatbuffer file" (#75244)
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)
2022-04-05 09:55:04 +00:00
d9d34922a0 Extend jit::load to work on flatbuffer file (#75022)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75022

Extending torch::jit::load to read flatbuffer file
ghstack-source-id: 152820697

Test Plan: CI

Reviewed By: iseeyuan

Differential Revision: D35060736

fbshipit-source-id: d653a5af662a46107ff4fd70209fd2a0a4d40f20
(cherry picked from commit 109e14a54bd279011c8f9066e6c29e8e0b1fc4db)
2022-04-02 01:33:34 +00:00
7aaa75af05 Extending _get_bytecode_version to support flatbuffers format (#75021)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75021

Extending `_get_bytecode_version` to support flatbuffers.
ghstack-source-id: 152771695

(Note: this ignores all push blocking failures!)

Test Plan:
```
~/fbsource/xplat] cd ~/fbsource/xplat/ && buck test //xplat/caffe2:test_lite_interpreter
Building: finished in 0.8 sec (100%) 327/327 jobs, 0/327 updated
  Total time: 0.9 sec
Testing: finished in 06:59.5 min (85 PASS/0 FAIL)
BUILD SUCCEEDED
RESULTS FOR //xplat/caffe2:test_lite_interpreter
PASS    412.3s 85 Passed   0 Skipped   0 Failed   //xplat/caffe2:test_lite_interpreter
TESTS PASSED
```

Reviewed By: iseeyuan

Differential Revision: D34900498

fbshipit-source-id: 65743076d43a933c5381ec128d0268f22c0a8441
(cherry picked from commit 457c76c7d1df6050b941c56a8198162e2e4a3388)
2022-04-01 15:05:37 +00:00
fc2cf3d26f Back out "Revert D34805092: Extend _save_for_mobile and _load_for_mobile to support flatbuffer format; Default format is pickle + Change buck targets to support only pickle and pickle + flatbuffer for migration" (#74594)
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)
2022-03-24 21:51:05 +00:00
c53b3ed20f Revert D34805092: Extend _save_for_mobile and _load_for_mobile to support flatbuffer format; Default format is pickle + Change buck targets to support only pickle and pickle + flatbuffer for migration
Test Plan: revert-hammer

Differential Revision:
D34805092 (284b2b7135)

Original commit changeset: 57f3fc81d68f

Original Phabricator Diff: D34805092 (284b2b7135)

fbshipit-source-id: 780dfb6fd6ba5f9348f24a2fb3c57971b7155541
(cherry picked from commit bebeb8b84e11c34cbde4857d0e1c291731a7c781)
2022-03-22 22:45:50 +00:00
284b2b7135 Extend _save_for_mobile and _load_for_mobile to support flatbuffer format; Default format is pickle + Change buck targets to support only pickle and pickle + flatbuffer for migration (#74209)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74209

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;
```
ghstack-source-id: 151744258

Test Plan:
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: D34805092

fbshipit-source-id: 57f3fc81d68fce941a050c35bd8e6f05951183b3
(cherry picked from commit 671ae4ed29e65b86ffe507a503548d3e86ab0ea4)
2022-03-22 20:00:53 +00:00
4b4f652f79 [3/5] Put JIT source inside flatbuffer (#74245)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74245

title

Test Plan: unittest

Reviewed By: iseeyuan

Differential Revision: D34881612

fbshipit-source-id: 7037982e9267ad72b86e91cd5f2d92426d71dd56
(cherry picked from commit 88f34eb55b2bee6ef8ef27188e075fa2b8767fdf)
2022-03-17 18:46:47 +00:00
62eb7d64cf [PyTorchEdge] Extend flatbuffer to support extra files map (#72951)
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)
2022-02-24 19:39:32 +00:00
57f039b41f Fixing few bugs in torch flatbuffer (#72349)
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 5e188093506aaf5ba64728364474ebde6e4d3d7c)
2022-02-05 00:25:27 +00:00
e926360cb8 [Pytorch Edge] Refactor Compatibility Stuff into own directory (#71432)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/71432

Organizing jit/mobile a little more

ghstack-source-id: 147184536

Test Plan: ci.

Reviewed By: iseeyuan

Differential Revision: D33640527

fbshipit-source-id: f3a7884fe0d06d80bb8d9cf141ecaee34b6f88ff
(cherry picked from commit 4c3d1e5435db04a4ca2898ddf0811490f5959555)
2022-01-20 19:38:41 +00:00
21b697b646 add flatbuffer_loader and flatbuffer_serializer as BUCK target (#71463)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/71463

title

Test Plan: unittest

Reviewed By: zhxchen17

Differential Revision: D33651339

fbshipit-source-id: 4bf325a40e263a441fd86bce560645ad0c1ebb23
(cherry picked from commit 4cb02e62a68f338e3388ad09276ced9b8f4cdcb1)
2022-01-20 04:51:10 +00:00
1bc3571078 [pytorch][PR] Add ability for a mobile::Module to save as flatbuffer (#70201)
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
2022-01-12 16:30:39 -08:00