huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-23 16:02:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore(trtllm): update dependency towards 0.15.0

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-12-04 12:02:42 +01:00
parent cc6bc339e5
commit b6dbf605af
3 changed files with 9 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
Dockerfile_trtllm
View File

@ -10,7 +10,7 @@ COPY . .
RUN cargo chef prepare --recipe-path recipe.json
# CUDA dependent dependencies resolver stage
FROM nvidia/cuda:12.6.1-cudnn-devel-ubuntu24.04 AS cuda-builder
FROM nvidia/cuda:12.6.3-cudnn-devel-ubuntu24.04 AS cuda-builder
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt,sharing=locked \
@ -18,8 +18,8 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
build-essential \
cmake \
curl \
gcc \
g++ \
gcc-14 \
g++-14 \
git \
git-lfs \
libssl-dev \
@ -86,7 +86,7 @@ RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$
cd backends/trtllm && \
CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --release
FROM nvidia/cuda:12.6.1-cudnn-runtime-ubuntu24.04 AS runtime
FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime
RUN apt update && apt install -y libucx0 pipx python3-minimal python3-dev python3-pip python3-venv && \
rm -rf /var/lib/{apt,dpkg,cache,log}/ && \
pipx ensurepath && \
@ -94,6 +94,7 @@ RUN apt update && apt install -y libucx0 pipx python3-minimal python3-dev python
WORKDIR /usr/local/tgi/bin
ENV PATH=/root/.local/share/pipx/venvs/transformers/bin/:$PATH
ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/mpi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH"
ENV TOKENIZERS_PARALLELISM=false
ENV OMPI_MCA_plm_rsh_agent=""

6
backends/trtllm/cmake/trtllm.cmake
View File

@ -25,9 +25,9 @@ find_package(Python3 REQUIRED Interpreter)
fetchcontent_declare(
trtllm
GIT_REPOSITORY https://github.com/NVIDIA/TensorRT-LLM.git
GIT_TAG 385626572df16175dd327fa785e4434cb7866a64
GIT_SHALLOW OFF
GIT_REPOSITORY https://github.com/huggingface/TensorRT-LLM.git
GIT_TAG 1bb9ca4688805444f203647674bac1d7219d0579
GIT_SHALLOW ON
DOWNLOAD_EXTRACT_TIMESTAMP
)
fetchcontent_makeavailable(trtllm)

2
backends/trtllm/scripts/install_tensorrt.sh
View File

@ -2,7 +2,7 @@
set -ex
TRT_VER_BASE="10.4.0"
TRT_VER_BASE="10.6.0"
TRT_VER_FULL="${TRT_VER_BASE}.26"
CUDA_VER="12.6"
CUDNN_VER="9.5.0.50-1"