mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
* [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>
99 lines
3.0 KiB
Bash
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
|