Collects some scattershot improvements made while attempting to enable training for AOTInductor. Non-typing changes are:
1. Swapping a few custom searches for the output node in an FX graph for calling `graph.output_node()`.
2. Removing two unused parameters from `torch.export._unlift._unlift`.
3. Switching handles to constants in `cpp_wrapper_cpu` to use C++ references for memory efficiency.
4. Cleaning out unused, unexported imports from `torch/export/__init__.py`, and adding one missing export to `__all__`.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/158075
Approved by: https://github.com/Skylion007
We package the weights and save them in `data/weights/` (`WEIGHTS_DIR`). In addition, we store a `weights_config.json` in the model folder for each model to specify which weight file corresponding to which weight name.
Models can share weights. We dedup the weights based on their underlying storage (`tensor.untyped_storate()`).
- Use `"aot_inductor.package_constants_on_disk": True` config to produce the `Weights` in aot_compile
- If we see `Weights` in aoti_files, we'll automatically package them to disk
- `"aot_inductor.package_constants_on_disk"` config and `"aot_inductor.package_constants_in_so"` config work independently.
- Use `load_pt2(package_path, load_weights_from_disk=True)` to load the weights from disk. `load_weights_from_disk` defaults to False.
Test Plan:
```
buck2 run @//mode/dev-nosan //caffe2/test/inductor:aot_inductor_package -- -r "test_package_shared_weights"
```
Tested with whisper at https://github.com/pytorch-labs/torchnative/pull/7
Rollback Plan:
Differential Revision: D74747190
Pull Request resolved: https://github.com/pytorch/pytorch/pull/155241
Approved by: https://github.com/desertfire
Refactor the pt2 archive saving to consolidate the format of torch.export.save and torch._inductor.package.package_aoti.
This PR adds the following functions, which torch.export.save and AOTI packaging calls into:
```python
package_pt2(
f: FileLike,
*,
exported_programs: Optional[Union[ExportedProgram, dict[str, ExportedProgram]]] = None,
aoti_files: Optional[Union[list[str], dict[str, list[str]]]] = None,
extra_files: Optional[dict[str, Any]] = None,
) -> FileLike
@dataclass
class PT2ArchiveContents:
exported_programs: dict[str, ExportedProgram]
aoti_runners: dict[str, AOTICompiledModel]
extra_files: dict[str, Any]
load_pt2(f: FileLike) -> PT2ArchiveContents
```
Power users directly call into these APIs if they want to bundle multiple exported programs, aoti files, or extra metadata.
This is how the pt2 archive looks like ([spec](https://docs.google.com/document/d/1RQ4cmywilnFUT1VE-4oTGxwXdc8vowCSZsrRgo3wFA8/edit?tab=t.0)):
```
├── archive_format
├── version
├── .data
├── data
│ ├── aotinductor
│ │ └── model1
│ │ ├── model1.cpp
│ │ ├── model1.so # currently AOTI automatically moves weights in here, TODO to move it out
│ │ ├── cg7domx3woam3nnliwud7yvtcencqctxkvvcafuriladwxw4nfiv.cubin
│ │ └── cubaaxppb6xmuqdm4bej55h2pftbce3bjyyvljxbtdfuolmv45ex.cubin
│ ├── weights
│ │ ├── model1.pt # TODO to dedup weights between model1/model2
│ │ └── model2.pt
│ └── constants
│ │ ├── model1.pt # TODO to dedup weights between model1/model2
│ │ └── model2.pt
│ └── sample_inputs
│ ├── model1.pt # TODO to dedup weights between model1/model2
│ └── model2.pt
├── extra
│ └── user_metadata.txt
└── models
├── model1.json
└── model2.json
```
Future todos:
- unbundle the weights -- instead of .pt, we can use bin files, which will also allow us to dedup weights if we store multiple models
- update aoti_compile_and_package to also save the exported program
- integrate TNR with this packaging flow
Pull Request resolved: https://github.com/pytorch/pytorch/pull/152495
Approved by: https://github.com/yushangdi
Summary:
Before:
`from sigmoid.core.package.pt2_archive import PT2ArchiveWriter, PT2ArchiveReader, is_sigmoid_package`
After:
`from torch.export.pt2_archive import PT2ArchiveWriter, PT2ArchiveReader, is_pt2_package`
By merging the two PT2ArchiveReader/Writers, into using the native PytorchFileReader/Writer, the open source PT2 archive also changed to have an additional folder. However this PR still maintains support for loading an old PT2 archive which does not have the additional folder.
Before:
```
├── archive_format
├── byteorder
├── .data
│ ├── serialization_id
│ └── version
├── data
│ ├── aotinductor
```
After:
```
├── tmp
│ ├── archive_format
│ ├── byteorder
│ ├── .data
│ │ ├── serialization_id
│ │ └── version
│ ├── data
│ │ ├── aotinductor
```
Test Plan:
`buck2 test //sigmoid/...`
https://www.internalfb.com/intern/testinfra/testrun/5348024839248187
Pull Request resolved: https://github.com/pytorch/pytorch/pull/153795
Approved by: https://github.com/zhxchen17
Summary:
Before:
`from sigmoid.core.package.pt2_archive import PT2ArchiveWriter, PT2ArchiveReader, is_sigmoid_package`
After:
`from torch.export.pt2_archive import PT2ArchiveWriter, PT2ArchiveReader, is_pt2_package`
By merging the two PT2ArchiveReader/Writers, into using the native PytorchFileReader/Writer, the open source PT2 archive also changed to have an additional folder. However this PR still maintains support for loading an old PT2 archive which does not have the additional folder.
Before:
```
├── archive_format
├── byteorder
├── .data
│ ├── serialization_id
│ └── version
├── data
│ ├── aotinductor
```
After:
```
├── tmp
│ ├── archive_format
│ ├── byteorder
│ ├── .data
│ │ ├── serialization_id
│ │ └── version
│ ├── data
│ │ ├── aotinductor
```
Test Plan:
`buck2 test //sigmoid/...`
https://www.internalfb.com/intern/testinfra/testrun/5348024839248187
Differential Revision: D74616598
Pull Request resolved: https://github.com/pytorch/pytorch/pull/153795
Approved by: https://github.com/zhxchen17
This is my suggestion for resolving #152087
This PR extends the constructor of `AOTIModelPackageLoader` with an (optional) device index. The device type is still determined by `metadata_["AOTI_DEVICE_KEY"]`, but the `device_index` argument can be used to move an AOTI model package to different devices like `cuda:0`, `cuda:1`, ... in a convenient way. AFAIK, this is not possible so far using `AOTIModelPackageLoader` alone. The default case (no device index specified) with `metadata_["AOTI_DEVICE_KEY"] == "cuda"` would lead to the current behavior, i.e., the model is loaded to device `cuda`.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/152093
Approved by: https://github.com/desertfire
Summary:
**Codegen**
- Skip some codegen parts for torchbind (such as arg decleration) because they are loaded in proxy executor, so we do not need to declare torchbind args in cpp code
- Added a helper method to get the schema of CallTorchBind HOP. The returned schema is only the schema of `obj.method()`.
**Serialization**
Add support for torchbind object in serialization
- For CallTorchBind HOP, we need to handle it specially because of it's schema. The output serialized args is in the format of `(obj, method, *args, **kwargs)`.
- it.TorchBindObject inputs are serialized to `as_custom_obj` Argument.
**Packaging**
Add torchbind objects file and `custom_objs_config.json` file to generated files output of `aot_compile`.
The json file is stored in the `data/aotinductor/<model_name>` folder in pt2 archive.
The torchbind objects are stored in data/constants/ folder in pt2 archive.
The format of torchbind objects are `f"{CUSTOM_OBJ_FILENAME_PREFIX}{custom_obj_idx}"`. e.g. `custom_obj_0`.
CustomClassHolder objects implement their own pickle methods.
Note that this `custom_objs_config.json` file is different from the `model_constants_config.json` file produced in package_sigmoid(). The keys in `custom_objs_config` directly correspond to the arg name in extern nodes json.
The key in `model_constants_config.json` produced by `package_sigmoid` is the attribute name in the user mode code.
This is required for both internal and OSS torchbind support.
For OSS torchbind support, we also need to package torchbind_constants into the .pt2 output.
**Work Left**
We still need to add torchbind support in ProxyExecutor for inductor.aoti_load_package to work. See other diffs in the stack.
Test Plan:
```
buck run fbcode//mode/dev-nosan //caffe2/test/inductor:torchbind -- -r schema
buck run fbcode//mode/dev-nosan //caffe2/test/inductor:torchbind -- -r aot_compile
```
Differential Revision: D69490718
Pull Request resolved: https://github.com/pytorch/pytorch/pull/148506
Approved by: https://github.com/angelayi
**Background**: I've been comparing performance of torch.compile vs. torch.export + AOTI (specifically, loaded from Python) on the Flux model and found a ~1.4% performance decrease with the latter. The trace shows that CUDAGraphs are not utilized for torch.export + AOTI, leading to higher overhead.
When trying to manually CUDAGraph the loaded, previously exported + AOTIed model (thanks to @eellison for the logic here), I get:
```
Error: operation not permitted when stream is capturing
```
@desertfire confirms that this is due to multi-threading logic on the AOTI runtime side (in `AOTIModelContainer` / `AOTIModel`) conflicting with the use of CUDAGraphs.
**Fix**: This PR takes the approach of providing an alternate, single-threaded method for running loaded models with the AOTI runtime. Details:
* Python side introduces a new flag to enable this behavior (needs a better name): `torch._inductor.package.load_package(..., run_single_threaded=False)`
* This flag is passed down to the C++ side's `AOTIModelPackageLoader`, which passes it to the `CreateAOTIModelRunnerFunc` during `AOTIModelContainerRunner` construction.
* C++ side introduces single-threaded alternatives to model running and model container running:
* `AOTIModelContainer.run_single_threaded()` / `AOTIModel.run_single_threaded()`. The interfaces match those of `run()`, but the synchronization logic has been removed.
* Introduces `AOTInductorModelContainerRunSingleThreaded` to AOTI's `interface.h`; this is invoked by the `AOTIModelContainerRunner` utility class when `run_single_threaded=true`.
I've verified on both a small repro and my real-world use case that I can manually CUDAGraph a loaded model that was previously exported + AOTIed.
**Future work:**
* Flip default value to `run_single_threaded=True` as Python-side inference doesn't take advantage of the AOTI runtime thread pool
* There are some BC concerns here - models need to be re-serialized so the .so contains the new `AOTInductorModelContainerRunSingleThreaded` interface func. We can flip the default value and warn (instead of crashing) if the `AOTInductorModelContainerRunSingleThreaded` symbol does not exist.
* Compose with cudagraph trees as opposed to manual cuda graph wrapping
Pull Request resolved: https://github.com/pytorch/pytorch/pull/148601
Approved by: https://github.com/desertfire
Fixes#144976
Using appoach ① `IO[bytes]`, but could also try with a protocol.
## Notes:
- moved `torch.serialization.FILE_LIKE` to `torch.types.FileLike`
- Use `FileLike` annotation where it makes sense
- made sure those functions also support `os.PathLike`
- Replaced `isinstance(x, io.BytesIO)` with `isinstance(x, (io.IOBase, IO))` where appropriate.
- Replaced `BinaryIO` with `IO[bytes]` (the two ABCs are almost identical, the only difference is that `BinaryIO` allows `bytearray` input to `write`, whereas `IO[bytes]` only `bytes`)
- needed to make `torch.serialization._opener` generic to avoid LSP violations.
- skipped `torch/onnx/verification` for now (functions use `BytesIO.getvalue` which is not part of the `IO[bytes]` ABC, but it kind of seems that this is redundant, as e.g. `onnx.load` supports `str | PathLike[str] | IO[bytes]` directly...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/144994
Approved by: https://github.com/ezyang, https://github.com/Skylion007
Summary:
With the changes in https://github.com/pytorch/pytorch/pull/140755 and https://github.com/pytorch/pytorch/pull/141997, I added a load_constants function to the packaging API. Currently this doesn't work for cpu.
The workflow is something like:
```
ep = torch.export.export(model, example_inputs)
package = torch._inductor.aoti_compile_and_package(ep, inductor_configs=inductor_configs)
compiled = torch._inductor.aoti_load_package(package)
print(compiled.get_constant_fqns()) # see what are the fqns needed/available
compiled.load_constants(new_state_dict, check_full_update=True) # update the constants in AOTI
```
You can also use the `aot_inductor.package_constants_in_so` config to stop including the constants in the so:
```
package = torch._inductor.aoti_compile_and_package(ep, inductor_configs={`aot_inductor.package_constants_in_so`: False)
compiled = torch._inductor.aoti_load_package(package)
compiled(*inputs) # segfaults because there are no constants --> we should probably have a better error msg
compiled.load_constants(new_state_dict, check_full_update=True)
compiled(*inputs)
```
Test Plan: `buck2 run @//mode/dev-nosan //caffe2/test/inductor:aot_inductor_package -- -r "test_so_without_weight" `
Differential Revision: D66796206
Pull Request resolved: https://github.com/pytorch/pytorch/pull/142246
Approved by: https://github.com/henrylhtsang, https://github.com/desertfire
* Added a cpp loader, AOTIModelPackageLoader, which can load the .pt2, build the .so, and create a runner. The python-facing API is that users can directly call the `run` function, whereas in cpp users can directly access the `runner_` if they are more familiar with that. I couldn't figure out how to bind the `get_runner()` function to python...
* Added a new config, `aot_inductor.package_cpp_only` which will **not** package the so. This means that whenever the package is loaded, we will need to build the so. This is turned off by default so that new environments do not need to rebuild their so. The `package_cpp_only` is a feature which torchchat intends to use to provide flexibility to users.
* Added a new config, `aot_inductor.metadata` which stores user-provided metadata, serialized to the pt2 as a json file. It also stores the device used when exporting, "cuda" or "cpu", so that during load time, we can use that data to determine which AOTIModelContainerRunner to use. The metadata can be accessed through `loader.get_metadata()`. TODO is to move this metadata to the toplevel `package_aoti` function so that we can remove the metadata as a config.
* Separated out `package_aoti` as a standalone function, instead of it automatically being called in inductor. This is to prepare for the case where users will compile multiple models, and want to bundle it in one package. The specific use case is in torchchat, where we want to package the separately-exported encoder and decoder layers. An example of how to use this is in `test_multiple_methods`.
* `load_package` will load a singular model, given the model name.
* The loader doesn't support windows for now, I think I need to add some more casing to make the build commands work on windows?
Differential Revision: [D62329906](https://our.internmc.facebook.com/intern/diff/D62329906)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/135374
Approved by: https://github.com/desertfire, https://github.com/malfet
In this PR, I added support for packaging the AOTI generated files into a zipfile, and loading it in python.
`compile_so` takes the path to the package, a device, and a desired so_path location, and compiles package into a .so, and saves to the specified location.
`load_package` takes a path to the package and device, calls _extract_so, and then creates a callable to run the compiled model.
The zipfile generated looks like the following:
```
|- version
|- archive_format
|- data
|- aotinductor
|- cbtnafqaqrhvwztv7xudlal4xs6sofxa5oxccyuaqtrt6aozaklx.cubin # AOTI cuda generated cubin files
|- cskkqtna23bty2v3aq7g2q37cxrgufehlkuaaolhlgug5zg6fuwe.cpp # AOTI generated cpp file
|- cskkqtna23bty2v3aq7g2q37cxrgufehlkuaaolhlgug5zg6fuwe_compile_flags # Flags for compiling the .o
|- c6qqtnpgwfi3dv5nb76ai773kt45ezoxfwdmd7q37lvq6fs2tnoi.o # AOTI saved const.o
|- cskkqtna23bty2v3aq7g2q37cxrgufehlkuaaolhlgug5zg6fuwe_linker_flags # Flags for linking the files to form the .so
|- constants
|- constants.pt # Constants saved using torch.save, can be loaded using mmap
```
The workflow is something like:
```
with torch.no_grad():
ep = torch.export.export(
model,
example_inputs,
dynamic_shapes=dynamic_shapes,
strict=False,
)
gm = ep.module()
package_path = torch._inductor.aot_compile(
gm,
example_inputs,
options= {
"aot_inductor.output_path": "my_path.pt2", # or a directory
"aot_inductor.package": True,
}
)
compiled_model = torch._inductor.package.load_package(package_path, device)
return compiled_model
```
I tried turning on loading the weights using mmap by default, but had some trouble with it, so that is just left as a todo
Pull Request resolved: https://github.com/pytorch/pytorch/pull/129895
Approved by: https://github.com/malfet
