Skip to content

feat: Update Pytorch version to 1.12 #1177

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

Merged
merged 3 commits into from
Jul 23, 2022
Merged

feat: Update Pytorch version to 1.12 #1177

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a18bb7c
feat: Update Pytorch version to 1.12
peri044 Jul 12, 2022
5d4bb28
chore: Resolve merge conflicts with master
peri044 Jul 23, 2022
dfd4a83
chore: Minor fix
peri044 Jul 23, 2022
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
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,7 @@ torch.jit.save(trt_ts_module, "trt_torchscript_module.ts") # save the TRT embedd
These are the following dependencies used to verify the testcases. Torch-TensorRT can work with other versions, but the tests are not guaranteed to pass.

- Bazel 5.1.1
- Libtorch 1.11.0 (built with CUDA 11.3)
- Libtorch 1.12.0 (built with CUDA 11.3)
- CUDA 11.3
- cuDNN 8.4.1
- TensorRT 8.4.1.5
Expand Down
8 changes: 4 additions & 4 deletions WORKSPACE
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,17 +56,17 @@ new_local_repository(
http_archive(
name = "libtorch",
build_file = "@//third_party/libtorch:BUILD",
sha256 = "8d9e829ce9478db4f35bdb7943308cf02e8a2f58cf9bb10f742462c1d57bf287",
sha256 = "80f089939de20e68e3fcad4dfa72a26c8bf91b5e77b11042f671f39ebac35865",
strip_prefix = "libtorch",
urls = ["https://download.pytorch.org/libtorch/cu113/libtorch-cxx11-abi-shared-with-deps-1.11.0%2Bcu113.zip"],
urls = ["https://download.pytorch.org/libtorch/cu113/libtorch-cxx11-abi-shared-with-deps-1.12.0%2Bcu113.zip"],
)

http_archive(
name = "libtorch_pre_cxx11_abi",
build_file = "@//third_party/libtorch:BUILD",
sha256 = "90159ecce3ff451f3ef3f657493b6c7c96759c3b74bbd70c1695f2ea2f81e1ad",
sha256 = "8e35371403f7052d9e9b43bcff383980dbde4df028986dc1dab539953481d55f",
strip_prefix = "libtorch",
urls = ["https://download.pytorch.org/libtorch/cu113/libtorch-shared-with-deps-1.11.0%2Bcu113.zip"],
urls = ["https://download.pytorch.org/libtorch/cu113/libtorch-shared-with-deps-1.12.0%2Bcu113.zip"],
)

# Download these tarballs manually from the NVIDIA website
Expand Down
2 changes: 1 addition & 1 deletion py/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
--extra-index-url https://download.pytorch.org/whl/cu113
torch==1.11.0
torch==1.12.0+cu113
pybind11==2.6.2
2 changes: 1 addition & 1 deletion py/torch_tensorrt/ts/_compile_spec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -350,7 +350,7 @@ def TensorRTCompileSpec(inputs=[],
backend_spec._set_workspace_size(parsed_spec.workspace_size)
backend_spec._set_dla_sram_size(parsed_spec.dla_sram_size)
backend_spec._set_dla_local_dram_size(parsed_spec.dla_local_dram_size)
backend_spec._set_dla_global_dram_size(parsed_spec._set_dla_global_dram_size)
backend_spec._set_dla_global_dram_size(parsed_spec.dla_global_dram_size)
backend_spec._set_truncate_long_and_double(parsed_spec.truncate_long_and_double)
backend_spec._set_ptq_calibrator(parsed_spec._get_calibrator_handle())

Expand Down
5 changes: 2 additions & 3 deletions tests/py/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,2 @@
torchvision==0.12.0
--extra-index-url https://download.pytorch.org/whl/cu113
pytest
torchvision==0.13.0+cu113
-f https://download.pytorch.org/whl/torch_stable.html