mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-21 23:12:07 +00:00
* (backend) use parking_lot crate for RwLock fairness
# Conflicts:
# backends/trtllm/src/backend.rs
* (launcher) default new server::run parameters to false for now
* (chore) fmt ... why?
* (ffi) use const for GetSamplingConfig
* (server) expose new SchedulingError
* (trt)
* (build) setup ccache if available
* (ffi) add max_new_tokens parameters
* (backend) cleanup a bit
* (backend) expose PullNewTokens
* (ffi) cleanup again
* (ffi) add missing headers imports
* (ffi) add template specialization to catch and convert to Rust Result<T, tensorrt_llm::common::TllmException>
* (looper) new looper initial implementation
* (ffi) remove narrowing type warning
* (ffi) encode the provided user prompt within each request thread
* (misc) change scope identifiers
* (backend) implement the post_processor background thread
* (misc) missing Result types for Rust
* use blocking_recv in looper to consume awaiting_requests at max before pulling in a single step
* (server) forward auth_token to server::run
* (build) fetchcontent use archives instead of git
* (ffi) fix usage of wrong vector constructor making a capacity fill call
* (ffi) missing namespace for tle::Response
* (ffi) do not use reference capture in lambda as we are not capturing anything
* (backend) refactor & cleanup
* (Dockerfile.trtllm) delete for now
* (misc) simplify [make_]move_iterator by using c++20 type inference
* (misc) no need to move for uint32_t items
* (scheduler) rework submit/pull logic
* (post) impl postprocessing
* (misc) delete backend.rs
* (misc) rerun-if-changed all the cmake modules
* (misc) move to latest trtllm
* (fix): HOPPER_SM_MAJOR is 9 not 8
* (misc: build for sm_{75,80,86,89,90} by default
* (misc): build with trtllm 0.13.0
* (misc): increase verbosity of spdlog
* (fix): do not recreate the stateful hashmap at every it
* (misc): update dependency in trtllm dockerfile
* (misc): update dependency in trtllm dockerfile
* (misc): disable logging in release mode
* (misc): improve trtllm download script robustness
* (fix): ore fixes for Dockerfile
* misc(cuda): require 12.6
* chore(cmake): use correct policy for download_timestamp
* feat(looper): check engine and executorWorker paths exist before creating the backend
* chore(cmake): download timestamp should be before URL
* feat(looper): minor optimizations to avoid growing too much the containers
* chore(trtllm): move dockerfile to right place
* chore(trtllm): disable tokenizer parallelism by default
* chore(trtllm): fmt
* chore(trtllm): post-rebase commit
* chore(trtllm): remove unused method
* feat(trtllm): cache maxNumTokens to avoid calling JSON everytime
* misc(router): remove SchedulingError
* feat(trtllm): do not tokenize twice
* Revert "chore(trtllm): remove unused method"
This reverts commit 31747163
* chore(rebase): fix invalid references
* chore(router): add python dependency
* Lint.
* Fix bad rebase
---------
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
114 lines
4.3 KiB
Bash
Executable File
114 lines
4.3 KiB
Bash
Executable File
#!/bin/bash
|
|
|
|
set -ex
|
|
|
|
TRT_VER_BASE="10.4.0"
|
|
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
|