From 478194b1b6fdf5fd37be015884a3571f7fff2f82 Mon Sep 17 00:00:00 2001
From: slaren <slarengh@gmail.com>
Date: Wed, 4 Dec 2024 01:10:37 +0100
Subject: [PATCH] update CPU dockerfiles

---
 .devops/full.Dockerfile         | 33 +++++++++++++++++++++++----------
 .devops/llama-cli.Dockerfile    | 18 ++++++++++++------
 .devops/llama-server.Dockerfile | 13 ++++++-------
 3 files changed, 41 insertions(+), 23 deletions(-)

diff --git a/.devops/full.Dockerfile b/.devops/full.Dockerfile
index 2a06f82b7..d93c0be6a 100644
--- a/.devops/full.Dockerfile
+++ b/.devops/full.Dockerfile
@@ -3,23 +3,36 @@ ARG UBUNTU_VERSION=22.04
 FROM ubuntu:$UBUNTU_VERSION AS build
 
 RUN apt-get update && \
-    apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1
-
-COPY requirements.txt   requirements.txt
-COPY requirements       requirements
-
-RUN pip install --upgrade pip setuptools wheel \
-    && pip install -r requirements.txt
+    apt-get install -y build-essential git cmake libcurl4-openssl-dev
 
 WORKDIR /app
 
 COPY . .
 
-ENV LLAMA_CURL=1
+RUN cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
+    cmake --build build -j $(nproc) && \
+    mkdir -p /app/lib && \
+    find build -name "*.so" -exec cp {} /app/lib/ \;
 
+FROM ubuntu:$UBUNTU_VERSION as runtime
 
-RUN make -j$(nproc)
+WORKDIR /app
+
+RUN apt-get update && \
+    apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1
+
+COPY requirements.txt   /app/requirements.txt
+COPY requirements       /app/requirements
+COPY .devops/tools.sh   /app/tools.sh
+
+RUN pip install --upgrade pip setuptools wheel && \
+    pip install -r /app/requirements.txt
+
+COPY --from=build /app/build/bin/ /app/
+COPY --from=build /app/lib/ /app/
+COPY --from=build /app/convert_hf_to_gguf.py /app/
+COPY --from=build /app/gguf-py /app/gguf-py
 
 ENV LC_ALL=C.utf8
 
-ENTRYPOINT ["/app/.devops/tools.sh"]
+ENTRYPOINT ["/app/tools.sh"]
diff --git a/.devops/llama-cli.Dockerfile b/.devops/llama-cli.Dockerfile
index 7f741aa46..be234d55d 100644
--- a/.devops/llama-cli.Dockerfile
+++ b/.devops/llama-cli.Dockerfile
@@ -3,21 +3,27 @@ ARG UBUNTU_VERSION=22.04
 FROM ubuntu:$UBUNTU_VERSION AS build
 
 RUN apt-get update && \
-    apt-get install -y build-essential git
+    apt-get install -y build-essential git cmake libcurl4-openssl-dev
 
 WORKDIR /app
 
 COPY . .
 
-RUN make -j$(nproc) llama-cli
+RUN cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
+    cmake --build build -j $(nproc) && \
+    mkdir -p /app/lib && \
+    find build -name "*.so" -exec cp {} /app/lib/ \;
 
 FROM ubuntu:$UBUNTU_VERSION AS runtime
 
-RUN apt-get update && \
-    apt-get install -y libgomp1
+WORKDIR /app
 
-COPY --from=build /app/llama-cli /llama-cli
+RUN apt-get update && \
+    apt-get install -y libcurl4-openssl-dev libgomp1 curl
+
+COPY --from=build /app/build/bin/llama-cli /app/
+COPY --from=build /app/lib/ /app/
 
 ENV LC_ALL=C.utf8
 
-ENTRYPOINT [ "/llama-cli" ]
+ENTRYPOINT [ "/app/llama-cli" ]
diff --git a/.devops/llama-server.Dockerfile b/.devops/llama-server.Dockerfile
index f6bda2ef8..72ccde2fe 100644
--- a/.devops/llama-server.Dockerfile
+++ b/.devops/llama-server.Dockerfile
@@ -9,21 +9,20 @@ WORKDIR /app
 
 COPY . .
 
-RUN \
-    # Build llama-server
-    cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
+RUN cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
     cmake --build build -j $(nproc) && \
-    # Copy the built libraries to /app/lib
     mkdir -p /app/lib && \
     find build -name "*.so" -exec cp {} /app/lib/ \;
 
 FROM ubuntu:$UBUNTU_VERSION AS runtime
 
+WORKDIR /app
+
 RUN apt-get update && \
     apt-get install -y libcurl4-openssl-dev libgomp1 curl
 
-COPY --from=build /app/build/bin/llama-server /llama-server
-COPY --from=build /app/lib/ /
+COPY --from=build /app/build/bin/llama-server /app/
+COPY --from=build /app/lib/ /app/
 
 ENV LC_ALL=C.utf8
 # Must be set to 0.0.0.0 so it can listen to requests from host machine
@@ -31,4 +30,4 @@ ENV LLAMA_ARG_HOST=0.0.0.0
 
 HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
 
-ENTRYPOINT [ "/llama-server" ]
+ENTRYPOINT [ "/app/llama-server" ]