Initial dockerisation

Dockerfile

@@ -0,0 +1,56 @@
+FROM nvidia/cuda:11.7.1-cudnn8-devel-ubuntu22.04
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update && \
+    apt-get upgrade -y && \
+    apt-get install -y --no-install-recommends \
+    git \
+    git-lfs \
+    wget \
+    curl \
+    # python build dependencies \
+    build-essential \
+    libssl-dev \
+    zlib1g-dev \
+    libbz2-dev \
+    libreadline-dev \
+    libsqlite3-dev \
+    libncursesw5-dev \
+    xz-utils \
+    tk-dev \
+    libxml2-dev \
+    libxmlsec1-dev \
+    libffi-dev \
+    liblzma-dev \
+    # gradio dependencies \
+    ffmpeg \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:${PATH}
+WORKDIR ${HOME}/app
+
+RUN curl https://pyenv.run | bash
+ENV PATH=${HOME}/.pyenv/shims:${HOME}/.pyenv/bin:${PATH}
+ARG PYTHON_VERSION=3.10.12
+RUN pyenv install ${PYTHON_VERSION} && \
+    pyenv global ${PYTHON_VERSION} && \
+    pyenv rehash && \
+    pip install --no-cache-dir -U pip setuptools wheel && \
+    pip install packaging ninja
+
+COPY --chown=1000 ./requirements.txt /tmp/requirements.txt
+RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt && \
+    pip install flash-attn --no-build-isolation
+
+COPY --chown=1000 src ${HOME}/app
+
+EXPOSE 7860
+CMD streamlit run app.py \
+    --server.headless true \
+    --server.enableCORS false \
+    --server.enableXsrfProtection false \
+    --server.fileWatcherType none

README.md

@@ -3,11 +3,6 @@ title: LLM ADE Dev
 emoji: 🔥
 colorFrom: pink
 colorTo: red
-sdk: streamlit
-sdk_version: 1.25.0
-app_file: app.py
-pinned: false
-license: apache-2.0
+sdk: docker
+port: 7860
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

packages.txt

@@ -0,0 +1,2 @@
+python3
+python3-pip

requirements.txt

@@ -1,3 +1,4 @@
+streamlit==1.34.0
 ninja==1.11.1.1
 numpy==1.26.4
 orjson==3.10.3

app.py → src/app.py

@@ -6,9 +6,6 @@ from utils import get_assistant_message
 from functioncall import ModelInference
 from prompter import PromptManager
 
-# HACK
-import subprocess
-subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
 @st.cache_resource(show_spinner="Loading model..")
 def init_llm():