Skip to content

Bump TRT version to 10.7 #3313

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 4 commits into from
Jan 2, 2025
Merged

Bump TRT version to 10.7 #3313

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
45407a6
add trt10.7 to workflow
zewenli98 Dec 6, 2024
1ef0133
bump to trt10.7
zewenli98 Dec 11, 2024
b79d234
small fix
zewenli98 Dec 18, 2024
98d5e93
keep trt related libs versions >=10.6.0,<10.8.0
zewenli98 Dec 31, 2024
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
10 changes: 10 additions & 0 deletions .github/scripts/generate-tensorrt-test-matrix.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,11 @@
"strip_prefix": "TensorRT-10.6.0.26",
"sha256": "6c6d92c108a1b3368423e8f69f08d31269830f1e4c9da43b37ba34a176797254",
},
"10.7.0": {
"urls": "https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.7.0/zip/TensorRT-10.7.0.23.Windows.win10.cuda-12.6.zip",
"strip_prefix": "TensorRT-10.7.0.23",
"sha256": "fbdef004578e7ccd5ee51fe7f846b57422364a743372fd8f9f1d7dbd33f62879",
},
},
"linux": {
"10.4.0": {
Expand All @@ -58,6 +63,11 @@
"strip_prefix": "TensorRT-10.6.0.26",
"sha256": "33d3c2f3f4c84dc7991a4337a6fde9ed33f5c8e5c4f03ac2eb6b994a382b03a0",
},
"10.7.0": {
"urls": "https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.7.0/tars/TensorRT-10.7.0.23.Linux.x86_64-gnu.cuda-12.6.tar.gz",
"strip_prefix": "TensorRT-10.7.0.23",
"sha256": "d7f16520457caaf97ad8a7e94d802f89d77aedf9f361a255f2c216e2a3a40a11",
},
},
}

Expand Down
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ Torch-TensorRT
[![Documentation](https://img.shields.io/badge/docs-master-brightgreen)](https://nvidia.github.io/Torch-TensorRT/)
[![pytorch](https://img.shields.io/badge/PyTorch-2.4-green)](https://www.python.org/downloads/release/python-31013/)
[![cuda](https://img.shields.io/badge/CUDA-12.4-green)](https://developer.nvidia.com/cuda-downloads)
[![trt](https://img.shields.io/badge/TensorRT-10.3.0-green)](https://github.com/nvidia/tensorrt-llm)
[![trt](https://img.shields.io/badge/TensorRT-10.7.0-green)](https://github.com/nvidia/tensorrt-llm)
[![license](https://img.shields.io/badge/license-BSD--3--Clause-blue)](./LICENSE)
[![linux_tests](https://github.com/pytorch/TensorRT/actions/workflows/build-test-linux.yml/badge.svg)](https://github.com/pytorch/TensorRT/actions/workflows/build-test-linux.yml)
[![windows_tests](https://github.com/pytorch/TensorRT/actions/workflows/build-test-windows.yml/badge.svg)](https://github.com/pytorch/TensorRT/actions/workflows/build-test-windows.yml)
Expand Down Expand Up @@ -119,7 +119,7 @@ These are the following dependencies used to verify the testcases. Torch-TensorR
- Bazel 6.3.2
- Libtorch 2.5.0.dev (latest nightly) (built with CUDA 12.4)
- CUDA 12.4
- TensorRT 10.6.0.26
- TensorRT 10.7.0.23

## Deprecation Policy

Expand Down
4 changes: 2 additions & 2 deletions dev_dep_versions.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
__cuda_version__: "12.4"
__tensorrt_version__: ">=10.3.0,<=10.6.0"
__cuda_version__: "12.6"
__tensorrt_version__: "10.7.0"
2 changes: 1 addition & 1 deletion packaging/smoke_test_script.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,5 +2,5 @@
# The issue was smoke test installs the built torch_tensorrt wheel file and checks `import torch_tensorrt; print(torch_tensorrt.__version__)`
# Since tensorrt cannot be pip installable in CI, the smoke test will fail.
# One way we tried to handle it is manually install tensorrt wheel while by extracting from the tarball.
# However, the TensorRT-10.3.0.26/lib path doesn't seem to show up in LD_LIBRARY_PATH even if we explicitly set it.
# However, the TensorRT-10.7.0.23/lib path doesn't seem to show up in LD_LIBRARY_PATH even if we explicitly set it.
# TODO: Implement a custom smoke_test script to verify torch_tensorrt installation.
13 changes: 7 additions & 6 deletions py/ci/Dockerfile.ci
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,13 +3,14 @@ FROM pytorch/manylinux2_28-builder:cuda12.6
RUN yum install -y ninja-build

# download TensorRT tarball
RUN wget -q https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.3.0/tars/TensorRT-10.3.0.26.Linux.x86_64-gnu.cuda-12.5.tar.gz \
&& gunzip TensorRT-10.3.0.26.Linux.x86_64-gnu.cuda-12.5.tar.gz \
&& tar -xvf TensorRT-10.3.0.26.Linux.x86_64-gnu.cuda-12.5.tar \
&& rm TensorRT-10.3.0.26.Linux.x86_64-gnu.cuda-12.5.tar
RUN wget -q https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.7.0/tars/TensorRT-10.7.0.23.Linux.x86_64-gnu.cuda-12.6.tar.gz \
&& gunzip TensorRT-10.7.0.23.Linux.x86_64-gnu.cuda-12.6.tar.gz \
&& tar -xvf TensorRT-10.7.0.23.Linux.x86_64-gnu.cuda-12.6.tar \
&& rm TensorRT-10.7.0.23.Linux.x86_64-gnu.cuda-12.6.tar

ENV TENSORRT_DIR=/TensorRT-10.3.0.26
ENV TENSORRT_VERSION=10.3.0
ENV TENSORRT_DIR=/TensorRT-10.7.0.23
ENV TENSORRT_VERSION=10.7.0
ENV USE_CXX11_ABI=1

RUN wget https://github.com/bazelbuild/bazelisk/releases/download/v1.17.0/bazelisk-linux-amd64 \
&& mv bazelisk-linux-amd64 /usr/bin/bazel \
Expand Down
8 changes: 4 additions & 4 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ requires = [
"cffi>=1.15.1",
"typing-extensions>=4.7.0",
"future>=0.18.3",
"tensorrt-cu12>=10.6.0,<10.8.0",
"tensorrt-cu12==10.7.0",
Copy link
Collaborator

Choose a reason for hiding this comment

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

Do multiple TRT versions get tested now in CI with this change ?

Copy link
Collaborator

Choose a reason for hiding this comment

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

It should right? Also 10.6 should be supported but we need at least 10.6 because of the QDP feature

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Do you mean we need to keep tensorrt-cu12>=10.6.0,<10.8.0?

Copy link
Collaborator

Choose a reason for hiding this comment

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

yeah

"torch>=2.6.0.dev,<2.7.0",
"pybind11==2.6.2",
"numpy",
Expand Down Expand Up @@ -55,9 +55,9 @@ keywords = [
]
dependencies = [
"torch>=2.6.0.dev,<2.7.0",
"tensorrt-cu12>=10.6.0,<10.8.0",
"tensorrt-cu12-bindings>=10.6.0,<10.8.0",
"tensorrt-cu12-libs>=10.6.0,<10.8.0",
"tensorrt-cu12==10.7.0",
"tensorrt-cu12-bindings==10.7.0",
"tensorrt-cu12-libs==10.7.0",
"packaging>=23",
"numpy",
"typing-extensions>=4.7.0",
Expand Down
10 changes: 4 additions & 6 deletions toolchains/ci_workspaces/MODULE.bazel.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,20 +67,18 @@ http_archive(
http_archive(
name = "tensorrt",
build_file = "@//third_party/tensorrt/archive:BUILD",
sha256 = "33d3c2f3f4c84dc7991a4337a6fde9ed33f5c8e5c4f03ac2eb6b994a382b03a0",
strip_prefix = "TensorRT-10.6.0.26",
strip_prefix = "TensorRT-10.7.0.23",
urls = [
"https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.6.0/tars/TensorRT-10.6.0.26.Linux.x86_64-gnu.cuda-12.6.tar.gz",
"https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.7.0/tars/TensorRT-10.7.0.23.Linux.x86_64-gnu.cuda-12.6.tar.gz",
],
)

http_archive(
name = "tensorrt_win",
build_file = "@//third_party/tensorrt/archive:BUILD",
sha256 = "6c6d92c108a1b3368423e8f69f08d31269830f1e4c9da43b37ba34a176797254",
strip_prefix = "TensorRT-10.6.0.26",
strip_prefix = "TensorRT-10.7.0.23",
urls = [
"https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.6.0/zip/TensorRT-10.6.0.26.Windows.win10.cuda-12.6.zip",
"https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.7.0/zip/TensorRT-10.7.0.23.Windows.win10.cuda-12.6.zip",
],
)

Expand Down
2 changes: 1 addition & 1 deletion toolchains/legacy/WORKSPACE.win.release.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@ http_archive(

new_local_repository(
name = "tensorrt_win",
path = "C:/TensorRT-10.3.0.26",
path = "C:/TensorRT-10.7.0.23",
build_file = "@//third_party/tensorrt/local:BUILD"
)

Expand Down
5 changes: 2 additions & 3 deletions toolchains/legacy/WORKSPACE.x86_64.release.rhel.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,10 +71,9 @@ http_archive(
http_archive(
name = "tensorrt",
build_file = "@//third_party/tensorrt/archive:BUILD",
sha256 = "adff1cd5abe5d87013806172351e58fd024e5bf0fc61d49ef4b84cd38ed99081",
strip_prefix = "TensorRT-10.3.0.26",
strip_prefix = "TensorRT-10.7.0.23",
urls = [
"https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.3.0/tars/TensorRT-10.3.0.26.Linux.x86_64-gnu.cuda-12.5.tar.gz",
"https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.7.0/tars/TensorRT-10.7.0.23.Linux.x86_64-gnu.cuda-12.6.tar.gz",
],
)

Expand Down
10 changes: 5 additions & 5 deletions uv.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading