frozenleaves/pytorch
1
0
Fork 0
mirror of https://github.com/pytorch/pytorch.git synced 2025-10-21 13:44:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

[jit] Scaffold a static runtime (#42753)

Browse Source 
Summary:
The premise of this approach is that a small subset of neural networks are well represented by a data flow graph.  The README contains more information.

The name is subject to change, but I thought it was a cute reference to fire.

suo let me know if you'd prefer this in a different spot.  Since it lowers a JIT'd module directly I assumed the JIT folder would be appropriate.  There is no exposed Python interface yet (but is mocked up in `test_accelerant.py`)

Pull Request resolved: https://github.com/pytorch/pytorch/pull/42753

Reviewed By: zou3519

Differential Revision: D23043771

Pulled By: bwasti

fbshipit-source-id: 5353731e3aae31c08b5b49820815da98113eb551
This commit is contained in:
Bram Wasti
2020-08-12 13:02:29 -07:00
committed by Facebook GitHub Bot
parent 59f8692350
commit ada8404f2d
8 changed files with 274 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
torch/csrc/jit/python/init.cpp
View File

@ -73,6 +73,7 @@
#include <torch/csrc/jit/runtime/jit_exception.h>
#include <torch/csrc/jit/runtime/operator.h>
#include <torch/csrc/jit/runtime/print_handler.h>
#include <torch/csrc/jit/runtime/static/init.h>
#include <torch/csrc/jit/serialization/export.h>
#include <torch/csrc/jit/serialization/import.h>
#include <torch/csrc/jit/tensorexpr/execution_counter.h>
@ -1091,6 +1092,7 @@ void initJITBindings(PyObject* module) {
initTreeViewBindings(module);
initJitScriptBindings(module);
initJitBackendBindings(module);
initStaticRuntimeBindings(module);
setPrintHandler([](const std::string& str) {
py::gil_scoped_acquire acquire;