Fixing TRTLLM dockerfile. (#2922)

* Fixing TRTLLM dockerfile.

* Fixed.

* Creating a dummy modification to chekc CI runs.

* Removing the cache directive.

* Modifying this should cache hit.

* Revert "Modifying this should cache hit."

This reverts commit 46a2bde108.

* Modifying this should cache hit.

* Unwanted files.

.devcontainer/Dockerfile_trtllm

@@ -1,75 +0,0 @@
-ARG CUDA_ARCH_LIST="75-real;80-real;86-real;89-real;90-real"
-ARG OMPI_VERSION="4.1.7rc1"
-
-# Build dependencies resolver stage
-FROM lukemathwalker/cargo-chef:latest AS chef
-WORKDIR /usr/src/text-generation-inference/backends/trtllm
-
-FROM chef AS planner
-COPY . .
-RUN cargo chef prepare --recipe-path recipe.json
-
-# CUDA dependent dependencies resolver stage
-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 \
-    apt update && apt install -y \
-    build-essential \
-    cmake \
-    curl \
-    gcc-14  \
-    g++-14 \
-    git \
-    git-lfs \
-    libssl-dev \
-    libucx-dev \
-    ninja-build \
-    pkg-config \
-    pipx \
-    python3 \
-    python3-dev \
-    python3-setuptools \
-    tar \
-    wget && \
-    pipx ensurepath
-
-ENV TGI_INSTALL_PREFIX=/usr/local/tgi
-ENV TENSORRT_INSTALL_PREFIX=/usr/local/tensorrt
-
-# Install OpenMPI
-FROM cuda-builder AS mpi-builder
-ARG OMPI_VERSION
-
-ENV OMPI_TARBALL_FILENAME="openmpi-$OMPI_VERSION.tar.bz2"
-RUN wget "https://download.open-mpi.org/release/open-mpi/v4.1/$OMPI_TARBALL_FILENAME" -P /opt/src && \
-    mkdir /usr/src/mpi && \
-    tar -xf "/opt/src/$OMPI_TARBALL_FILENAME" -C /usr/src/mpi --strip-components=1 && \
-    cd /usr/src/mpi && \
-    ./configure --prefix=/usr/local/mpi --with-cuda=/usr/local/cuda --with-slurm && \
-    make -j all && \
-    make install && \
-    rm -rf "/opt/src/$OMPI_TARBALL_FILENAME"
-
-# Install TensorRT
-FROM cuda-builder AS trt-builder
-COPY backends/trtllm/scripts/install_tensorrt.sh /opt/install_tensorrt.sh
-RUN chmod +x /opt/install_tensorrt.sh && \
-    /opt/install_tensorrt.sh
-
-# Build Backend
-FROM cuda-builder AS tgi-builder
-WORKDIR /usr/src/text-generation-inference
-
-# Install Rust
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | bash -s -- -y && \
-    chmod -R a+w /root/.rustup && \
-    chmod -R a+w /root/.cargo
-
-ENV PATH="/root/.cargo/bin:$PATH"
-RUN cargo install cargo-chef
-
-COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
-COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
-
-ENV MPI_HOME=/usr/local/mpi

.devcontainer/devcontainer.json

@@ -1,19 +0,0 @@
-// For format details, see https://aka.ms/devcontainer.json. For config options, see the
-// README at: https://github.com/devcontainers/templates/tree/main/src/cpp
-{
-  "name": "CUDA",
-  "build": {
-    "dockerfile": "Dockerfile_trtllm",
-    "context": ".."
-  },
-  "remoteEnv": {
-    "PATH": "${containerEnv:PATH}:/usr/local/cuda/bin",
-    "LD_LIBRARY_PATH": "$LD_LIBRARY_PATH:/usr/local/cuda/lib64:/usr/local/cuda/extras/CUPTI/lib64",
-    "XLA_FLAGS": "--xla_gpu_cuda_data_dir=/usr/local/cuda"
-  },
-  "customizations" : {
-    "jetbrains" : {
-      "backend" : "CLion"
-    }
-  }
-}

Dockerfile_trtllm

@@ -6,15 +6,19 @@ FROM lukemathwalker/cargo-chef:latest-rust-1.84.0 AS chef
 WORKDIR /usr/src/text-generation-inference/backends/trtllm
 
 FROM chef AS planner
-COPY . .
+COPY Cargo.lock Cargo.lock
+COPY Cargo.toml Cargo.toml
+COPY rust-toolchain.toml rust-toolchain.toml
+COPY router router
+COPY benchmark/ benchmark/
+COPY backends/ backends/
+COPY launcher/ launcher/
 RUN cargo chef prepare --recipe-path recipe.json
 
 # CUDA dependent dependencies resolver stage
 FROM nvidia/cuda:12.6.3-cudnn-devel-ubuntu24.04 AS cuda-builder
 
-RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
-    --mount=type=cache,target=/var/lib/apt,sharing=locked \
-    apt update && apt install -y \
     build-essential \
     cmake \
     curl \
@@ -31,7 +35,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
     python3-dev \
     python3-setuptools \
     tar \
-    wget && \
+    wget --no-install-recommends && \
     pipx ensurepath
 
 ENV TGI_INSTALL_PREFIX=/usr/local/tgi
@@ -79,7 +83,11 @@ ENV CMAKE_PREFIX_PATH="/usr/local/mpi:/usr/local/tensorrt:$CMAKE_PREFIX_PATH"
 ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
 ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig:$PKG_CONFIG_PATH"
 
-COPY . .
+COPY Cargo.lock Cargo.lock
+COPY Cargo.toml Cargo.toml
+COPY rust-toolchain.toml rust-toolchain.toml
+COPY router router
+COPY backends/trtllm backends/trtllm
 COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
 COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
 RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \

server/text_generation_server/cli.py

@@ -9,6 +9,8 @@ from enum import Enum
 from huggingface_hub import hf_hub_download
 from text_generation_server.utils.adapter import parse_lora_adapters
 
+# Dummy change should cache hit.
+
 
 app = typer.Typer()