[inference][issue-67] support pip install in docker container (intel#81)

* [inference][issue-67] support pip install in docker container

Signed-off-by: Jiafu Zhang <[email protected]>

* [inference][issue-67] support pip install in docker container
add one more pip non-editable test for real user case

Signed-off-by: Jiafu Zhang <[email protected]>

* [inference][issue-67] support pip install in docker container
add one more pip non-editable test for real user case - gpt-j-6b

Signed-off-by: Jiafu Zhang <[email protected]>

* [inference][issue-67] support pip install in docker container
revert unintentional changes

Signed-off-by: Jiafu Zhang <[email protected]>

---------

Signed-off-by: Jiafu Zhang <[email protected]>

.github/workflows/workflow_inference.yml

@@ -84,6 +84,8 @@ jobs:
             DF_SUFFIX=".bigdl-cpu"
           elif [[ ${{ matrix.model }} == "llama-2-7b-chat-hf-vllm" ]]; then
             DF_SUFFIX=".vllm"
+          elif [[ ${{ matrix.model }} == "gpt-j-6b" ]]; then
+            DF_SUFFIX=".cpu_and_deepspeed.pip_non_editable"
           else
             DF_SUFFIX=".cpu_and_deepspeed"
           fi

MANIFEST.in

@@ -0,0 +1,2 @@
+# with [tools.setuptools] in pyproject.toml, the configs below work in both baremetal and container
+include inference/**/*.yaml

dev/docker/Dockerfile.bigdl-cpu

@@ -25,6 +25,7 @@ RUN --mount=type=cache,target=/opt/conda/pkgs conda init bash && \
     conda install python==3.9
 
 COPY ./pyproject.toml .
+COPY ./MANIFEST.in .
 
 RUN mkdir ./finetune && mkdir ./inference
 

dev/docker/Dockerfile.cpu_and_deepspeed

@@ -25,6 +25,7 @@ RUN --mount=type=cache,target=/opt/conda/pkgs conda init bash && \
     conda install python==3.9
 
 COPY ./pyproject.toml .
+COPY ./MANIFEST.in .
 
 RUN mkdir ./finetune && mkdir ./inference
 

dev/docker/Dockerfile.cpu_and_deepspeed.pip_non_editable

@@ -0,0 +1,38 @@
+# syntax=docker/dockerfile:1
+FROM ubuntu:22.04
+
+ENV LANG C.UTF-8
+
+WORKDIR /root/llm-on-ray
+
+RUN --mount=type=cache,target=/var/cache/apt apt-get update -y \
+    && apt-get install -y build-essential cmake wget curl git vim htop ssh net-tools \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+ENV CONDA_DIR /opt/conda
+RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda.sh && \
+    /bin/bash ~/miniconda.sh -b -p /opt/conda
+ENV PATH $CONDA_DIR/bin:$PATH
+
+# setup env
+SHELL ["/bin/bash", "--login", "-c"]
+
+RUN --mount=type=cache,target=/opt/conda/pkgs conda init bash && \
+    unset -f conda && \
+    export PATH=$CONDA_DIR/bin/:${PATH} && \
+    conda config --add channels intel && \
+    conda install python==3.9
+
+# copy all checkedout file for later non-editable pip
+COPY . .
+
+RUN --mount=type=cache,target=/root/.cache/pip pip install .[cpu,deepspeed] -f https://developer.intel.com/ipex-whl-stable-cpu \
+    -f https://download.pytorch.org/whl/torch_stable.html
+
+RUN ds_report
+
+# Used to invalidate docker build cache with --build-arg CACHEBUST=$(date +%s)
+ARG CACHEBUST=1
+COPY ./dev/scripts/install-oneapi.sh /tmp
+RUN /tmp/install-oneapi.sh

dev/docker/Dockerfile.vllm

@@ -25,6 +25,7 @@ RUN --mount=type=cache,target=/opt/conda/pkgs conda init bash && \
     conda install -y -c conda-forge python==3.9 gxx=12.3 gxx_linux-64=12.3
 
 COPY ./pyproject.toml .
+COPY ./MANIFEST.in .
 COPY ./dev/scripts/install-vllm-cpu.sh .
 
 RUN mkdir ./finetune && mkdir ./inference

pyproject.toml

@@ -73,7 +73,9 @@ ui = [
 ]
 
 [tool.setuptools]
-packages = ["finetune", "inference"]
+# with MANIFEST.in, the configs below work in both baremetal and container
+package-dir = {"inference" = "inference", "finetune" = "finetune"}
+include-package-data = true
 
 [project.urls]
 Repository = "https://github.com/intel/llm-on-ray.git"