TensorRT-LLMs/docker/common/install_pytorch.sh
Daniel Cámpora 41ce5440fe
chore: Mass integration of release/0.18 (#3421)
* [Infra][TRTLLM-4063] - Branch out for the TRT-LLM v0.18.0 release

Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com>
(cherry picked from commit de90312020e51c22ba5e75b3502c7ee90c059265)

* [Infra][TRTLLM-3652] - Update dependencies to TRT 10.9 / CUDA 12.8.1 / DLFW 25.03(Internal)

Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
(cherry picked from commit 58db1340ef7db22f1910f878d220a92be5b830d1)

* [None][Doc] - Update docs for v0.18.0

Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
(cherry picked from commit d23e75bc95619ce3b116213d55319272888e0c88)

* [Infra] - Fix or WAR issues in the package sanity check stages

Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
(cherry picked from commit e874e2b127515c52ba10c8df1cc2631627f74ffe)

* [https://nvbugs/5173454] [https://nvbugs/5173432] [https://nvbugs/5175863] fix chatglm tokenizer and tmp model path

Signed-off-by: Yuki Huang <yukih@nvidia.com>
(cherry picked from commit 731811d4e182d70a66193d646152cb71dfafe83a)

* cherry-pick 'test: Updat cluster and multi node test lists and trtllm-bench' test to fix perf drop issue

Signed-off-by: Ruodi Lu <ruodil@nvidia.com>
(cherry picked from commit 5214616283fbc15ae98871a1d84c78d8e1f2e6e8)

* Revert "Merge branch 'user/yukih/fix_5173454_5173432' into 'release/0.18'"

Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
(cherry picked from commit 8d34831cb2b81ee2dfa8021b68e7158b33789a5f)

* [Infra]Restrict setuptools version to avoid sasb pip install issue

Signed-off-by: Emma Qiao <qqiao@nvidia.com>
(cherry picked from commit 1e60ad29e0dafec0e295bedb5d89b716a02a707c)

* [https://nvbugs/5173454] [https://nvbugs/5173432] [https://nvbugs/5175863] fix chatglm tokenizer and tmp model path

Signed-off-by: Yuki Huang <yukih@nvidia.com>
(cherry picked from commit 3ed8164e5bfea1d5aa2039b5408439fd6cf59dac)

* WAR for bug 5173448

Signed-off-by: Thor Johnsen <tjohnsen@nvidia.com>
(cherry picked from commit b6528b2ba15322b6c6a4c81a8b74c04d4973de4f)

* [Infra][TRTLLM-3652] - Update dependencies to CUDA 12.8.1 / DLFW 25.03

Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
(cherry picked from commit 6560983d132d9d257ee15849664eb055e94adaa9)

* [Docs] - Doc changes for v0.18.0

Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
(cherry picked from commit 26769b61218a947c8f9d070f73b63d576fcc20c4)

* [Doc] - Doc change for v0.18.0

Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
(cherry picked from commit 4b3b5ed6bfbc2300e3775fe75456083faad7b235)

* [Infra] update version to 0.18.1

Signed-off-by: Zhanrui Sun <zhanruis@nvidia.com>
(cherry picked from commit 59e8326c75639275837d34de8e140358737a3365)

* Add back nemotron file.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Fix recurrentgemma reqs.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Adding WAR for bug 5173448.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Formatting.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Remove duplicated file.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Update examples/prompt_lookup/requirements.txt

Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com>

* Remove glm-4-9b from model dir in chatglm test.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Remove indent change.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com>

* Revert changes on l0_test.groovy.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Update dev images

Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>

* Remove duplicated import.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Fix custom op

Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>

* Fix flashinfer & vanilla backend

Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>

* Skip problematic case.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

* Skip problematic test_moe_w4a8_1_14336_4096_8_bfloat16_True_False case.

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

---------

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com>
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
Signed-off-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
Co-authored-by: Zhanrui Sun <zhanruis@nvidia.com>
Co-authored-by: Yiqing Yan <yiqingy@nvidia.com>
Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>
Co-authored-by: Yuki Huang <yukih@nvidia.com>
Co-authored-by: Ruodi Lu <ruodil@nvidia.com>
Co-authored-by: Emma Qiao <qqiao@nvidia.com>
Co-authored-by: Thor Johnsen <tjohnsen@nvidia.com>
Co-authored-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
Co-authored-by: Yi Zhang <187001205+yizhang-nv@users.noreply.github.com>
Co-authored-by: Tao Li @ NVIDIA <tali@nvidia.com>
2025-04-16 10:03:29 +08:00

99 lines
3.0 KiB
Bash

#!/bin/bash
set -ex
# Use latest stable version from https://pypi.org/project/torch/#history
# and closest to the version specified in
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-25-03.html#rel-25-03
TORCH_VERSION="2.6.0"
SYSTEM_ID=$(grep -oP '(?<=^ID=).+' /etc/os-release | tr -d '"')
prepare_environment() {
if [[ $SYSTEM_ID == *"ubuntu"* ]]; then
apt-get update && apt-get -y install ninja-build
apt-get clean && rm -rf /var/lib/apt/lists/*
elif [[ $SYSTEM_ID == *"rocky"* ]]; then
dnf makecache --refresh && dnf install -y ninja-build && dnf clean all
else
echo "This system type cannot be supported..."
exit 1
fi
}
install_from_source() {
if [[ $SYSTEM_ID == *"rocky"* ]]; then
VERSION_ID=$(grep -oP '(?<=^VERSION_ID=).+' /etc/os-release | tr -d '"')
if [[ $VERSION_ID == "7" ]]; then
echo "Installation from PyTorch source codes cannot be supported..."
exit 1
fi
fi
ARCH=$(uname -m)
if [ "$ARCH" = "amd64" ];then ARCH="x86_64";fi
if [ "$ARCH" = "aarch64" ];then ARCH="sbsa";fi
if [ "$ARCH" = "sbsa" ] && [ "$TORCH_VERSION" = "2.6.0" ]; then
echo "Due to a known issue https://github.com/pytorch/pytorch/issues/141083, PyTorch v2.6.0 installation from source codes cannot be supported..."
exit 1
fi
prepare_environment $1
export _GLIBCXX_USE_CXX11_ABI=$1
export TORCH_CUDA_ARCH_LIST="8.0;9.0"
export PYTORCH_BUILD_VERSION=${TORCH_VERSION}
export PYTORCH_BUILD_NUMBER=0
pip3 uninstall -y torch
cd /tmp
git clone --depth 1 --branch v${TORCH_VERSION} https://github.com/pytorch/pytorch
cd pytorch
git submodule sync && git submodule update --init --recursive
pip3 install -r requirements.txt
python3 setup.py install
cd /tmp && rm -rf /tmp/pytorch
# Get torchvision version by dry run
TORCHVISION_VERSION=$(pip3 install --dry-run torch==${TORCH_VERSION} torchvision | grep "Would install" | tr ' ' '\n' | grep torchvision | cut -d "-" -f 2)
export PYTORCH_VERSION=${PYTORCH_BUILD_VERSION}
export FORCE_CUDA=1
export BUILD_VERSION=${TORCHVISION_VERSION}
pip3 uninstall -y torchvision
cd /tmp
git clone --depth 1 --branch v${TORCHVISION_VERSION} https://github.com/pytorch/vision
cd vision
python3 setup.py install
cd /tmp && rm -rf /tmp/vision
}
install_from_pypi() {
ARCH=$(uname -m)
if [ "$ARCH" = "amd64" ];then ARCH="x86_64";fi
if [ "$ARCH" = "aarch64" ];then ARCH="sbsa";fi
pip3 uninstall -y torch torchvision
if [ "$ARCH" = "sbsa" ]; then
pip3 install torch==${TORCH_VERSION} torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
else
pip3 install torch==${TORCH_VERSION} torchvision
fi
}
case "$1" in
"skip")
;;
"pypi")
install_from_pypi
;;
"src_cxx11_abi")
install_from_source 1
;;
"src_non_cxx11_abi")
install_from_source 0
;;
*)
echo "Incorrect input argument..."
exit 1
;;
esac