From 1ef01330fc5c0ec771877cbaefc7470b011ac111 Mon Sep 17 00:00:00 2001 From: Evan Li Date: Wed, 11 Dec 2024 13:26:34 -0800 Subject: [PATCH] bump to trt10.7 --- .../scripts/generate-tensorrt-test-matrix.py | 2 +- README.md | 4 ++-- dev_dep_versions.yml | 4 ++-- packaging/smoke_test_script.sh | 2 +- py/ci/Dockerfile.ci | 13 ++++++------ pyproject.toml | 10 ++++++++++ toolchains/ci_workspaces/MODULE.bazel.tmpl | 10 ++++------ toolchains/legacy/WORKSPACE.win.release.tmpl | 2 +- .../legacy/WORKSPACE.x86_64.release.rhel.tmpl | 6 +++--- uv.lock | 20 +++++++++++++------ 10 files changed, 45 insertions(+), 28 deletions(-) diff --git a/.github/scripts/generate-tensorrt-test-matrix.py b/.github/scripts/generate-tensorrt-test-matrix.py index ae92faf591..6beea4d0dc 100644 --- a/.github/scripts/generate-tensorrt-test-matrix.py +++ b/.github/scripts/generate-tensorrt-test-matrix.py @@ -66,7 +66,7 @@ "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": "27d0f7e9af657b9fa19bfe9d62376d4de64182ed6274bde04bf143f56d308ec9", + "sha256": "d7f16520457caaf97ad8a7e94d802f89d77aedf9f361a255f2c216e2a3a40a11", }, }, } diff --git a/README.md b/README.md index 5ee8dd4df7..7312ecbd5a 100644 --- a/README.md +++ b/README.md @@ -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) @@ -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 diff --git a/dev_dep_versions.yml b/dev_dep_versions.yml index 527b83936e..b921d558fd 100644 --- a/dev_dep_versions.yml +++ b/dev_dep_versions.yml @@ -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" diff --git a/packaging/smoke_test_script.sh b/packaging/smoke_test_script.sh index 19d9d717a4..ef584fef51 100644 --- a/packaging/smoke_test_script.sh +++ b/packaging/smoke_test_script.sh @@ -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. \ No newline at end of file diff --git a/py/ci/Dockerfile.ci b/py/ci/Dockerfile.ci index 823c8bb7a1..288c61029d 100644 --- a/py/ci/Dockerfile.ci +++ b/py/ci/Dockerfile.ci @@ -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 \ diff --git a/pyproject.toml b/pyproject.toml index 6cc3412849..966e9b1f68 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -8,7 +8,11 @@ requires = [ "cffi>=1.15.1", "typing-extensions>=4.7.0", "future>=0.18.3", +<<<<<<< HEAD "tensorrt-cu12>=10.6.0,<10.8.0", +======= + "tensorrt-cu12==10.7.0", +>>>>>>> 78af8f69c (bump to trt10.7) "torch>=2.6.0.dev,<2.7.0", "pybind11==2.6.2", "numpy", @@ -55,9 +59,15 @@ keywords = [ ] dependencies = [ "torch>=2.6.0.dev,<2.7.0", +<<<<<<< HEAD "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", +>>>>>>> 78af8f69c (bump to trt10.7) "packaging>=23", "numpy", "typing-extensions>=4.7.0", diff --git a/toolchains/ci_workspaces/MODULE.bazel.tmpl b/toolchains/ci_workspaces/MODULE.bazel.tmpl index 142a021609..66b5d448ca 100644 --- a/toolchains/ci_workspaces/MODULE.bazel.tmpl +++ b/toolchains/ci_workspaces/MODULE.bazel.tmpl @@ -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", ], ) diff --git a/toolchains/legacy/WORKSPACE.win.release.tmpl b/toolchains/legacy/WORKSPACE.win.release.tmpl index 58fce5cf54..5570516c6c 100644 --- a/toolchains/legacy/WORKSPACE.win.release.tmpl +++ b/toolchains/legacy/WORKSPACE.win.release.tmpl @@ -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" ) diff --git a/toolchains/legacy/WORKSPACE.x86_64.release.rhel.tmpl b/toolchains/legacy/WORKSPACE.x86_64.release.rhel.tmpl index 97b3a8c566..0574002b7e 100644 --- a/toolchains/legacy/WORKSPACE.x86_64.release.rhel.tmpl +++ b/toolchains/legacy/WORKSPACE.x86_64.release.rhel.tmpl @@ -71,10 +71,10 @@ http_archive( http_archive( name = "tensorrt", build_file = "@//third_party/tensorrt/archive:BUILD", - sha256 = "adff1cd5abe5d87013806172351e58fd024e5bf0fc61d49ef4b84cd38ed99081", - strip_prefix = "TensorRT-10.3.0.26", + sha256 = "d7f16520457caaf97ad8a7e94d802f89d77aedf9f361a255f2c216e2a3a40a11", + 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", ], ) diff --git a/uv.lock b/uv.lock index c4d4f776f4..aaaee57247 100644 --- a/uv.lock +++ b/uv.lock @@ -378,7 +378,6 @@ dependencies = [ { name = "markupsafe", marker = "sys_platform == 'linux' or sys_platform == 'windows'" }, ] wheels = [ - { url = "https://download.pytorch.org/whl/nightly/Jinja2-3.1.4-py3-none-any.whl" }, { url = "https://download.pytorch.org/whl/nightly/jinja2-3.1.4-py3-none-any.whl" }, ] @@ -633,6 +632,15 @@ wheels = [ { url = "https://download.pytorch.org/whl/nightly/cu126/nvidia_cusparselt_cu12-0.6.3-py3-none-manylinux2014_x86_64.whl" }, ] +[[package]] +name = "nvidia-cusparselt-cu12" +version = "0.6.2" +source = { registry = "https://download.pytorch.org/whl/nightly/cu124" } +wheels = [ + { url = "https://download.pytorch.org/whl/nightly/cu124/nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_aarch64.whl" }, + { url = "https://download.pytorch.org/whl/nightly/cu124/nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_x86_64.whl" }, +] + [[package]] name = "nvidia-modelopt" version = "0.17.0" @@ -1372,11 +1380,11 @@ requires-dist = [ { name = "packaging", specifier = ">=23" }, { name = "rich", marker = "extra == 'monitoring-tools'", specifier = ">=13.7.1" }, { name = "rich", extras = ["jupyter"], marker = "extra == 'jupyter'", specifier = ">=13.7.1" }, - { name = "tensorrt-cu12", specifier = ">=10.6.0,<10.8.0" }, - { name = "tensorrt-cu12-bindings", specifier = ">=10.6.0,<10.8.0" }, - { name = "tensorrt-cu12-libs", specifier = ">=10.6.0,<10.8.0" }, - { name = "torch", specifier = ">=2.6.0.dev0,<2.7.0", index = "https://download.pytorch.org/whl/nightly/cu126" }, - { name = "torchvision", marker = "extra == 'torchvision'", index = "https://download.pytorch.org/whl/nightly/cu126" }, + { name = "tensorrt-cu12", specifier = "==10.7.0" }, + { name = "tensorrt-cu12-bindings", specifier = "==10.7.0" }, + { name = "tensorrt-cu12-libs", specifier = "==10.7.0" }, + { name = "torch", specifier = ">=2.6.0.dev0,<2.7.0" }, + { name = "torchvision", marker = "extra == 'torchvision'" }, { name = "typing-extensions", specifier = ">=4.7.0" }, ]