LLaMA-Factory-310P3/docker/docker-rocm/Dockerfile

58 lines
1.6 KiB
Docker

FROM hardandheavy/transformers-rocm:2.1.0
# Define environments
ENV MAX_JOBS=4
ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
# Define installation arguments
ARG INSTALL_BNB=false
ARG INSTALL_VLLM=false
ARG INSTALL_DEEPSPEED=false
ARG INSTALL_FLASHATTN=false
ARG PIP_INDEX=https://pypi.org/simple
# Set the working directory
WORKDIR /app
# Install the requirements
COPY requirements.txt /app
RUN pip config set global.index-url "$PIP_INDEX" && \
pip config set global.extra-index-url "$PIP_INDEX" && \
python -m pip install --upgrade pip && \
python -m pip install -r requirements.txt
# Copy the rest of the application into the image
COPY . /app
# Install the LLaMA Factory
RUN EXTRA_PACKAGES="metrics"; \
if [ "$INSTALL_BNB" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},bitsandbytes"; \
fi; \
if [ "$INSTALL_VLLM" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},vllm"; \
fi; \
if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
fi; \
pip install -e ".[$EXTRA_PACKAGES]"
# Rebuild flash attention
RUN pip uninstall -y transformer-engine flash-attn && \
if [ "$INSTALL_FLASHATTN" == "true" ]; then \
pip uninstall -y ninja && pip install ninja && \
pip install --no-cache-dir flash-attn --no-build-isolation; \
fi
# Set up volumes
VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
# Expose port 7860 for the LLaMA Board
ENV GRADIO_SERVER_PORT 7860
EXPOSE 7860
# Expose port 8000 for the API service
ENV API_PORT 8000
EXPOSE 8000