Skip to content

Use a CUDAGuard when running Torch models #340

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Use a CUDAGuard when running Torch models #340

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions source/neuropod/backends/torchscript/torch_backend.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,10 @@
#include "neuropod/backends/torchscript/type_utils.hh"
#include "neuropod/internal/tensor_types.hh"

#ifndef __APPLE__
#include <c10/cuda/CUDAGuard.h>
#endif

#include <caffe2/core/macros.h>

#include <iostream>
Expand Down Expand Up @@ -291,6 +295,16 @@ std::unique_ptr<NeuropodValueMap> TorchNeuropodBackend::infer_internal(const Neu
{
torch::NoGradGuard guard;

#ifndef __APPLE__
// Make sure we're running on the correct device
std::unique_ptr<at::cuda::CUDAGuard> device_guard;
Copy link
Contributor

@vkuzmin-uber vkuzmin-uber Aug 31, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

#include <memory>

const auto model_device = get_torch_device(DeviceType::GPU);
if (model_device.is_cuda())
{
device_guard = stdx::make_unique<at::cuda::CUDAGuard>(model_device);
Copy link
Contributor

@vkuzmin-uber vkuzmin-uber Aug 31, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I guess we can use std:: here not stdx:: because Neuropod became C++14 recently, right?

}
#endif

// Get inference schema
const auto &method = model_->get_method("forward");
const auto &schema = SCHEMA(method);
Expand Down