mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-21 05:34:18 +08:00
ada8404f2d
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
25 lines
704 B
C++
25 lines
704 B
C++
#include <torch/csrc/jit/runtime/static/impl.h>
|
|
#include <torch/csrc/jit/runtime/static/init.h>
|
|
|
|
namespace torch {
|
|
namespace jit {
|
|
|
|
void initStaticRuntimeBindings(PyObject* module) {
|
|
auto m = py::handle(module).cast<py::module>();
|
|
py::class_<StaticRuntime>(m, "StaticRuntime").def("run", &StaticRuntime::run);
|
|
m.def(
|
|
"_jit_to_static_runtime",
|
|
[](const std::shared_ptr<torch::jit::Graph>& g) {
|
|
return StaticRuntime(g);
|
|
})
|
|
.def(
|
|
"_jit_to_static_runtime",
|
|
[](const torch::jit::Module& m,
|
|
const std::shared_ptr<torch::jit::Graph>& g) {
|
|
return StaticRuntime(m, g);
|
|
});
|
|
}
|
|
|
|
} // namespace jit
|
|
} // namespace torch
|