Docker with llama.cpp

Dockerfile

@@ -0,0 +1,43 @@
+FROM python:3.10.14
+
+# Install some assorted build and dev libraries
+ARG DEBIAN_FRONTEND=noninteractive
+ENV TZ=Europe/Paris
+RUN apt-get update && apt-get install -y \
+        git \
+		jq \
+        make build-essential libssl-dev zlib1g-dev \
+        libbz2-dev libreadline-dev libsqlite3-dev wget curl llvm \
+        libncursesw5-dev xz-utils tk-dev libxml2-dev libxmlsec1-dev libffi-dev liblzma-dev
+
+# User
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME /home/user
+ENV PATH $HOME/.local/bin:$PATH
+WORKDIR $HOME
+RUN mkdir app
+WORKDIR $HOME/app
+
+# Build llama.cpp (CPU, only `quantize`)
+# Should we pin a known commit?
+RUN git clone https://github.com/ggerganov/llama.cpp.git
+WORKDIR $HOME/app/llama.cpp
+RUN make quantize
+WORKDIR $HOME/app
+
+# App and Python reqs
+# Should we pin versions here?
+COPY --chown=user ./ $HOME/app
+RUN pip install --no-cache-dir -r requirements.txt
+
+# These may be enough to trigger a gradio Space
+#ENV PYTHONPATH $HOME/app
+#ENV PYTHONUNBUFFERED 1
+#ENV GRADIO_ALLOW_FLAGGING never
+#ENV GRADIO_NUM_PORTS 1
+#ENV GRADIO_SERVER_NAME 0.0.0.0
+#ENV GRADIO_THEME huggingface
+#ENV SYSTEM spaces
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,7 @@
+import gradio as gr
+
+def greet(name):
+    return "Hello " + name + "!"
+
+demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+huggingface-hub