Update Dockerfile

Dockerfile

@@ -1,24 +1,113 @@
-ARG UBUNTU_VERSION=22.04
+ARG CUDA_IMAGE="12.1.1-devel-ubuntu22.04"
+FROM nvidia/cuda:${CUDA_IMAGE}
 
-FROM ubuntu:$UBUNTU_VERSION as build
+# We need to set the host to 0.0.0.0 to allow outside access
+ENV HOST 0.0.0.0
 
-RUN apt-get update && \
-    apt-get install -y build-essential git
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y git build-essential \
+    python3 python3-pip gcc wget \
+    ocl-icd-opencl-dev opencl-headers clinfo \
+    libclblast-dev libopenblas-dev \
+    && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
 
-RUN git clone https://github.com/ggerganov/llama.cpp
+COPY . .
 
-WORKDIR /llama.cpp
+# setting build related env vars
+ENV CUDA_DOCKER_ARCH=all
+ENV LLAMA_CUBLAS=1
 
-RUN make
+# Install depencencies
+RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings gradio huggingface_hub hf_transfer
 
-COPY . .
+# Install llama-cpp-python (build with cuda)
+# RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python
+RUN FORCE_CMAKE=1 pip install llama-cpp-python
+
+RUN useradd -m -u 1000 user
+# Switch to the "user" user
+USER user
+# Set home to the user's home directory
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH \
+    PYTHONPATH=$HOME/app \
+	PYTHONUNBUFFERED=1 \
+	GRADIO_ALLOW_FLAGGING=never \
+	GRADIO_NUM_PORTS=1 \
+	GRADIO_SERVER_NAME=0.0.0.0 \
+	GRADIO_THEME=huggingface \
+	SYSTEM=spaces
+
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
+
+CMD ["python3", "app.py"]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+# ARG UBUNTU_VERSION=22.04
+
+# FROM ubuntu:$UBUNTU_VERSION as build
+
+# RUN apt-get update && \
+#     apt-get install -y build-essential git
+
+# RUN git clone https://github.com/ggerganov/llama.cpp
+
+# WORKDIR /llama.cpp
+
+# RUN make
+
+# COPY . .
 
-# FROM ubuntu:$UBUNTU_VERSION as runtime
+# # FROM ubuntu:$UBUNTU_VERSION as runtime
 
-# COPY --from=build /llama.cpp/main /main
+# # COPY --from=build /llama.cpp/main /main
 
-ENV LC_ALL=C.utf8
+# ENV LC_ALL=C.utf8
 
-ENTRYPOINT ["/main", "-m", "./models/ggml-model-q4_1.gguf", "-p", "### Instruction:\nତୁମେ କିଏ?\n\n### Response:\n"]
+# ENTRYPOINT ["/main", "-m", "./models/ggml-model-q4_1.gguf", "-p", "### Instruction:\nତୁମେ କିଏ?\n\n### Response:\n"]
 
-# ./main -ngl 16 -m /content/openllama_odia_3b_base/ggml-model-q5_1.gguf -n 512 -p  "### Instruction:\nତୁମେ କିଏ?\n\n### Response:\n"
+# # ./main -ngl 16 -m /content/openllama_odia_3b_base/ggml-model-q5_1.gguf -n 512 -p  "### Instruction:\nତୁମେ କିଏ?\n\n### Response:\n"