huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-22 15:32:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

(fix): ore fixes for Dockerfile

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-10-10 16:24:38 +00:00 committed by Morgan Funtowicz
parent f9f10a6636
commit dd94ccc989
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
backends/trtllm/Dockerfile
View File

@ -10,7 +10,7 @@ COPY . .
RUN cargo chef prepare --recipe-path recipe.json RUN cargo chef prepare --recipe-path recipe.json
# CUDA dependent dependencies resolver stage # CUDA dependent dependencies resolver stage
FROM nvidia/cuda:12.6.1-cudnn-devel-ubuntu24.04 AS cuda-builder FROM nvidia/cuda:12.6.1-cudnn-devel-ubuntu22.04 AS cuda-builder
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt,sharing=locked \ --mount=type=cache,target=/var/lib/apt,sharing=locked \
@ -82,7 +82,7 @@ RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$
cd backends/trtllm && \ cd backends/trtllm && \
CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --release CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --release
FROM nvidia/cuda:12.6.1-cudnn-runtime-ubuntu24.04 AS runtime FROM nvidia/cuda:12.6.1-cudnn-runtime-ubuntu22.04 AS runtime
WORKDIR /usr/local/tgi/bin WORKDIR /usr/local/tgi/bin
ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH" ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH"

2
backends/trtllm/build.rs
View File

@ -6,7 +6,7 @@ use std::path::{absolute, PathBuf};
const ADDITIONAL_BACKEND_LINK_LIBRARIES: [&str; 2] = ["spdlog", "fmt"]; const ADDITIONAL_BACKEND_LINK_LIBRARIES: [&str; 2] = ["spdlog", "fmt"];
const CUDA_ARCH_LIST: Option<&str> = option_env!("CUDA_ARCH_LIST"); const CUDA_ARCH_LIST: Option<&str> = option_env!("CUDA_ARCH_LIST");
const CUDA_REQUIRED_VERSION: &str = "12.5"; const CUDA_REQUIRED_VERSION: &str = "12.6";
const MPI_REQUIRED_VERSION: &str = "4.1"; const MPI_REQUIRED_VERSION: &str = "4.1";
const INSTALL_PREFIX: Option<&str> = option_env!("CMAKE_INSTALL_PREFIX"); const INSTALL_PREFIX: Option<&str> = option_env!("CMAKE_INSTALL_PREFIX");
const TENSORRT_ROOT_DIR: Option<&str> = option_env!("TENSORRT_ROOT_DIR"); const TENSORRT_ROOT_DIR: Option<&str> = option_env!("TENSORRT_ROOT_DIR");