text-generation-inference/backends/trtllm/scripts/install_tensorrt.sh
Funtowicz Morgan ea7f4082c4
TensorRT-LLM backend bump to latest version + misc fixes (#2791)
* misc(cmake) update dependencies

* feat(hardware) enable new hardware.hpp and unittests

* test(ctest) enable address sanitizer

* feat(backend): initial rewrite of the backend for simplicity

* feat(backend): remove all the logs from hardware.hpp

* feat(backend): added some logging

* feat(backend): enable compiler warning if support for RVO not applying

* feat(backend): missing return statement

* feat(backend): introduce backend_workspace_t to store precomputed information from the engine folder

* feat(backend): delete previous backend impl

* feat(backend): more impl

* feat(backend): use latest trtllm main version to have g++ >= 13 compatibility

* feat(backend): allow overriding which Python to use

* feat(backend): fix backend_exception_t -> backend_error_t naming

* feat(backend): impl missing generation_step_t as return value of pull_tokens

* feat(backend): make backend_workspace_t::engines_folder constexpr

* feat(backend): fix main.rs retrieving the tokenizer

* feat(backend): add guard to multiple header definitions

* test(backend): add more unittest

* feat(backend): remove constexpr from par

* feat(backend): remove constexpig

* test(backend): more test coverage

* chore(trtllm): update dependency towards 0.15.0

* effectively cancel the request on the executor

* feat(backend) fix moving backend when pulling

* feat(backend): make sure we can easily cancel request on the executor

* feat(backend): fix missing "0" field access

* misc(backend): fix reborrowing Pin<&mut T> as described in the doc https://doc.rust-lang.org/stable/std/pin/struct.Pin.html#method.as_mut

* chore: Add doc and CI for TRTLLM (#2799)

* chore: Add doc and CI for TRTLLM

* chore: Add doc and CI for TRTLLM

* chore: Add doc and CI for TRTLLM

* chore: Add doc and CI for TRTLLM

* doc: Formatting

* misc(backend): indent

---------

Co-authored-by: Hugo Larcher <hugo.larcher@huggingface.co>
2024-12-13 15:50:59 +01:00

114 lines
4.3 KiB
Bash
Executable File

#!/bin/bash
set -ex
TRT_VER_BASE="10.6.0"
TRT_VER_FULL="${TRT_VER_BASE}.26"
CUDA_VER="12.6"
CUDNN_VER="9.5.0.50-1"
NCCL_VER="2.22.3-1+cuda12.6"
CUBLAS_VER="12.6.3.3-1"
NVRTC_VER="12.6.77-1"
for i in "$@"; do
case $i in
--TRT_VER=?*) TRT_VER="${i#*=}";;
--CUDA_VER=?*) CUDA_VER="${i#*=}";;
--CUDNN_VER=?*) CUDNN_VER="${i#*=}";;
--NCCL_VER=?*) NCCL_VER="${i#*=}";;
--CUBLAS_VER=?*) CUBLAS_VER="${i#*=}";;
*) ;;
esac
shift
done
NVCC_VERSION_OUTPUT=$(nvcc --version)
if [[ $(echo $NVCC_VERSION_OUTPUT | grep -oP "\d+\.\d+" | head -n 1) != ${CUDA_VER} ]]; then
echo "The version of pre-installed CUDA is not equal to ${CUDA_VER}."
exit 1
fi
install_ubuntu_requirements() {
apt-get update && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates
ARCH=$(uname -m)
if [ "$ARCH" = "amd64" ];then ARCH="x86_64";fi
if [ "$ARCH" = "aarch64" ];then ARCH="sbsa";fi
curl -fsSLO https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${ARCH}/cuda-keyring_1.1-1_all.deb
dpkg -i cuda-keyring_1.1-1_all.deb
rm /etc/apt/sources.list.d/cuda-ubuntu2404-x86_64.list
apt-get update
if [[ $(apt list --installed | grep libcudnn9) ]]; then
apt-get remove --purge -y --allow-change-held-packages libcudnn9*
fi
if [[ $(apt list --installed | grep libnccl) ]]; then
apt-get remove --purge -y --allow-change-held-packages libnccl*
fi
if [[ $(apt list --installed | grep libcublas) ]]; then
apt-get remove --purge -y --allow-change-held-packages libcublas*
fi
if [[ $(apt list --installed | grep cuda-nvrtc-dev) ]]; then
apt-get remove --purge -y --allow-change-held-packages cuda-nvrtc-dev*
fi
CUBLAS_CUDA_VERSION=$(echo $CUDA_VER | sed 's/\./-/g')
apt-get install -y --no-install-recommends libcudnn9-cuda-12=${CUDNN_VER} libcudnn9-dev-cuda-12=${CUDNN_VER}
apt-get install -y --no-install-recommends libnccl2=${NCCL_VER} libnccl-dev=${NCCL_VER}
apt-get install -y --no-install-recommends libcublas-${CUBLAS_CUDA_VERSION}=${CUBLAS_VER} libcublas-dev-${CUBLAS_CUDA_VERSION}=${CUBLAS_VER}
# NVRTC static library doesn't exist in NGC PyTorch container.
NVRTC_CUDA_VERSION=$(echo $CUDA_VER | sed 's/\./-/g')
apt-get install -y --no-install-recommends cuda-nvrtc-dev-${NVRTC_CUDA_VERSION}=${NVRTC_VER}
apt-get clean
rm -rf /var/lib/apt/lists/*
}
install_centos_requirements() {
CUBLAS_CUDA_VERSION=$(echo $CUDA_VER | sed 's/\./-/g')
yum -y update
yum -y install epel-release
yum remove -y libnccl* && yum -y install libnccl-${NCCL_VER} libnccl-devel-${NCCL_VER}
yum remove -y libcublas* && yum -y install libcublas-${CUBLAS_CUDA_VERSION}-${CUBLAS_VER} libcublas-devel-${CUBLAS_CUDA_VERSION}-${CUBLAS_VER}
yum clean all
}
install_tensorrt() {
#PY_VERSION=$(python3 -c 'import sys; print(".".join(map(str, sys.version_info[0:2])))')
#PARSED_PY_VERSION=$(echo "${PY_VERSION//./}")
TRT_CUDA_VERSION="12.6"
if [ -z "$RELEASE_URL_TRT" ];then
ARCH=${TRT_TARGETARCH}
if [ -z "$ARCH" ];then ARCH=$(uname -m);fi
if [ "$ARCH" = "arm64" ];then ARCH="aarch64";fi
if [ "$ARCH" = "amd64" ];then ARCH="x86_64";fi
if [ "$ARCH" = "x86_64" ];then DIR_NAME="x64-agnostic"; else DIR_NAME=${ARCH};fi
if [ "$ARCH" = "aarch64" ];then OS1="Ubuntu22_04" && OS2="Ubuntu-24.04" && OS="ubuntu-24.04"; else OS1="Linux" && OS2="Linux" && OS="linux";fi
RELEASE_URL_TRT=https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/${TRT_VER_BASE}/tars/TensorRT-${TRT_VER_FULL}.${OS2}.${ARCH}-gnu.cuda-${TRT_CUDA_VERSION}.tar.gz
fi
wget --no-verbose ${RELEASE_URL_TRT} -O /tmp/TensorRT.tar
tar -xf /tmp/TensorRT.tar -C /usr/local/
mv /usr/local/TensorRT-${TRT_VER_FULL} /usr/local/tensorrt
# pip3 install /usr/local/tensorrt/python/tensorrt-*-cp${PARSED_PY_VERSION}-*.whl
rm -rf /tmp/TensorRT.tar
}
# Install base packages depending on the base OS
ID=$(grep -oP '(?<=^ID=).+' /etc/os-release | tr -d '"')
case "$ID" in
debian)
install_ubuntu_requirements
install_tensorrt
;;
ubuntu)
install_ubuntu_requirements
install_tensorrt
;;
centos)
install_centos_requirements
install_tensorrt
;;
*)
echo "Unable to determine OS..."
exit 1
;;
esac