mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-11-04 18:02:19 +08:00
102 lines
3.0 KiB
Docker
102 lines
3.0 KiB
Docker
# Default use the NVIDIA official image with PyTorch 2.3.0
|
|
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/index.html
|
|
ARG BASE_IMAGE=nvcr.io/nvidia/pytorch:24.02-py3
|
|
FROM ${BASE_IMAGE}
|
|
|
|
# Define environments
|
|
ENV MAX_JOBS=4
|
|
ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
|
|
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
|
|
# Define installation arguments
|
|
ARG INSTALL_BNB=false
|
|
ARG INSTALL_VLLM=false
|
|
ARG INSTALL_DEEPSPEED=false
|
|
ARG INSTALL_FLASHATTN=false
|
|
ARG INSTALL_LIGER_KERNEL=false
|
|
ARG INSTALL_HQQ=false
|
|
ARG INSTALL_EETQ=false
|
|
ARG PIP_INDEX=https://pypi.org/simple
|
|
ARG HTTP_PROXY=
|
|
|
|
# Set the working directory
|
|
WORKDIR /app
|
|
|
|
# Set http proxy
|
|
RUN if [ -n "$HTTP_PROXY" ]; then \
|
|
echo "Configuring proxy..."; \
|
|
export http_proxy=$HTTP_PROXY; \
|
|
export https_proxy=$HTTP_PROXY; \
|
|
fi
|
|
|
|
# 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 && \
|
|
if [ -n "$HTTP_PROXY" ]; then \
|
|
python -m pip install --proxy=$HTTP_PROXY -r requirements.txt; \
|
|
else \
|
|
python -m pip install -r requirements.txt; \
|
|
fi
|
|
|
|
# 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; \
|
|
if [ "$INSTALL_LIGER_KERNEL" == "true" ]; then \
|
|
EXTRA_PACKAGES="${EXTRA_PACKAGES},liger-kernel"; \
|
|
fi; \
|
|
if [ "$INSTALL_HQQ" == "true" ]; then \
|
|
EXTRA_PACKAGES="${EXTRA_PACKAGES},hqq"; \
|
|
fi; \
|
|
if [ "$INSTALL_EETQ" == "true" ]; then \
|
|
EXTRA_PACKAGES="${EXTRA_PACKAGES},eetq"; \
|
|
fi; \
|
|
if [ -n "$HTTP_PROXY" ]; then \
|
|
pip install --proxy=$HTTP_PROXY -e ".[$EXTRA_PACKAGES]"; \
|
|
else \
|
|
pip install -e ".[$EXTRA_PACKAGES]"; \
|
|
fi
|
|
|
|
# Rebuild flash attention
|
|
RUN pip uninstall -y transformer-engine flash-attn && \
|
|
if [ "$INSTALL_FLASHATTN" == "true" ]; then \
|
|
pip uninstall -y ninja && \
|
|
if [ -n "$HTTP_PROXY" ]; then \
|
|
pip install --proxy=$HTTP_PROXY ninja && \
|
|
pip install --proxy=$HTTP_PROXY --no-cache-dir flash-attn --no-build-isolation; \
|
|
else \
|
|
pip install ninja && \
|
|
pip install --no-cache-dir flash-attn --no-build-isolation; \
|
|
fi; \
|
|
fi
|
|
|
|
|
|
# Unset http proxy
|
|
RUN if [ -n "$HTTP_PROXY" ]; then \
|
|
unset http_proxy; \
|
|
unset https_proxy; \
|
|
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
|