add uv axolotl builds (#3431)
This commit is contained in:
Wing Lian
GitHub
@@ -59,34 +59,18 @@ RUN git lfs install --skip-repo && \
|
||||
pip3 install -U --no-cache-dir pydantic==1.10.10 && \
|
||||
pip3 cache purge
|
||||
|
||||
RUN case "$PYTORCH_VERSION" in \
|
||||
2.9.[0-9]*) \
|
||||
if [ "$CUDA" = "128" ]; then \
|
||||
if [ "$TARGETARCH" = "amd64" ]; then \
|
||||
WHL_FILE="flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl"; \
|
||||
WHL_VERSION="v0.5.4"; \
|
||||
elif [ "$TARGETARCH" = "arm64" ]; then \
|
||||
WHL_FILE="flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_aarch64.whl"; \
|
||||
WHL_VERSION="v0.6.4"; \
|
||||
else \
|
||||
echo "Unsupported architecture: $TARGETARCH"; exit 1; \
|
||||
fi; \
|
||||
wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/${WHL_VERSION}/${WHL_FILE}; \
|
||||
pip3 install --no-cache-dir ${WHL_FILE}; \
|
||||
rm ${WHL_FILE}; \
|
||||
elif [ "$CUDA" = "130" ]; then \
|
||||
if [ "$TARGETARCH" = "amd64" ]; then \
|
||||
WHL_FILE="flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl"; \
|
||||
WHL_VERSION="v0.5.4"; \
|
||||
elif [ "$TARGETARCH" = "arm64" ]; then \
|
||||
WHL_FILE="flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_aarch64.whl"; \
|
||||
WHL_VERSION="v0.6.4"; \
|
||||
else \
|
||||
echo "Unsupported architecture: $TARGETARCH"; exit 1; \
|
||||
fi; \
|
||||
wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/${WHL_VERSION}/${WHL_FILE}; \
|
||||
pip3 install --no-cache-dir ${WHL_FILE}; \
|
||||
rm ${WHL_FILE}; \
|
||||
fi \
|
||||
;; \
|
||||
esac
|
||||
# Map Python version (e.g., 3.12 -> cp312)
|
||||
RUN PYTHON_CP="cp$(echo $PYTHON_VERSION | tr -d '.')" && \
|
||||
# Map PyTorch version (e.g., 2.9.1 -> torch2.9, 2.10.0 -> torch2.10)
|
||||
TORCH_TAG="torch$(echo $PYTORCH_VERSION | grep -oP '^\d+\.\d+')" && \
|
||||
# Map architecture
|
||||
case "$TARGETARCH" in \
|
||||
amd64) ARCH_TAG="x86_64" ;; \
|
||||
arm64) ARCH_TAG="aarch64" ;; \
|
||||
*) echo "Unsupported architecture: $TARGETARCH"; exit 1 ;; \
|
||||
esac && \
|
||||
WHL_VERSION="v0.7.16" && \
|
||||
WHL_FILE="flash_attn-2.8.3+cu${CUDA}${TORCH_TAG}-${PYTHON_CP}-${PYTHON_CP}-linux_${ARCH_TAG}.whl" && \
|
||||
wget -nv "https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/${WHL_VERSION}/${WHL_FILE}" && \
|
||||
pip3 install --no-cache-dir "${WHL_FILE}" && \
|
||||
rm "${WHL_FILE}"
|
||||
|
||||
30
docker/Dockerfile-cloud-uv
Normal file
30
docker/Dockerfile-cloud-uv
Normal file
@@ -0,0 +1,30 @@
|
||||
ARG BASE_TAG=main
|
||||
FROM axolotlai/axolotl-uv:$BASE_TAG
|
||||
|
||||
ENV HF_DATASETS_CACHE="/workspace/data/huggingface-cache/datasets"
|
||||
ENV HF_HUB_CACHE="/workspace/data/huggingface-cache/hub"
|
||||
ENV HF_HOME="/workspace/data/huggingface-cache/hub"
|
||||
ENV HF_HUB_ENABLE_HF_TRANSFER="1"
|
||||
|
||||
EXPOSE 8888
|
||||
EXPOSE 22
|
||||
|
||||
COPY scripts/cloud-entrypoint.sh /root/cloud-entrypoint.sh
|
||||
COPY scripts/motd /etc/motd
|
||||
|
||||
RUN pip install jupyterlab notebook ipywidgets && \
|
||||
jupyter lab clean
|
||||
RUN apt update && \
|
||||
apt install --yes --no-install-recommends openssh-server tmux iproute2 nvtop && \
|
||||
rm -rf /var/cache/apt/archives && \
|
||||
rm -rf /var/lib/apt/lists/* && \
|
||||
mkdir -p ~/.ssh && \
|
||||
chmod 700 ~/.ssh && \
|
||||
printf "\n[[ -z \"\$TMUX\" ]] && { tmux attach-session -t ssh_tmux || tmux new-session -s ssh_tmux; exit; }\n" >> ~/.bashrc && \
|
||||
printf "[ ! -z \"\$TERM\" -a -r /etc/motd ] && cat /etc/motd\n" >> ~/.bashrc && \
|
||||
chmod +x /workspace/axolotl/scripts/cloud-entrypoint.sh && \
|
||||
chmod +x /root/cloud-entrypoint.sh && \
|
||||
echo 'set-option -g history-limit 5000' >> ~/.tmux.conf
|
||||
|
||||
ENTRYPOINT ["/root/cloud-entrypoint.sh"]
|
||||
CMD ["sleep", "infinity"]
|
||||
47
docker/Dockerfile-uv
Normal file
47
docker/Dockerfile-uv
Normal file
@@ -0,0 +1,47 @@
|
||||
ARG BASE_TAG=main-base
|
||||
FROM axolotlai/axolotl-base-uv:$BASE_TAG
|
||||
|
||||
ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
|
||||
ARG AXOLOTL_EXTRAS=""
|
||||
ARG AXOLOTL_ARGS=""
|
||||
ARG CUDA="118"
|
||||
ARG PYTORCH_VERSION="2.1.2"
|
||||
ARG TARGETARCH
|
||||
|
||||
ENV PYTORCH_VERSION=$PYTORCH_VERSION
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev rsync s3fs && \
|
||||
rm -rf /var/cache/apt/archives && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
WORKDIR /workspace
|
||||
|
||||
RUN git clone --depth=1 https://github.com/axolotl-ai-cloud/axolotl.git
|
||||
|
||||
WORKDIR /workspace/axolotl
|
||||
|
||||
# If AXOLOTL_EXTRAS is set, append it in brackets; don't install deepspeed with arm64
|
||||
RUN if [ "$TARGETARCH" = "arm64" ]; then \
|
||||
BASE_EXTRAS="flash-attn,ring-flash-attn,optimizers,ray"; \
|
||||
else \
|
||||
BASE_EXTRAS="deepspeed,flash-attn,ring-flash-attn,optimizers,ray"; \
|
||||
fi && \
|
||||
if [ "$AXOLOTL_EXTRAS" != "" ]; then \
|
||||
uv pip install --no-build-isolation -e .[$BASE_EXTRAS,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
|
||||
else \
|
||||
uv pip install --no-build-isolation -e .[$BASE_EXTRAS] $AXOLOTL_ARGS; \
|
||||
fi && \
|
||||
python scripts/unsloth_install.py --uv | sh && \
|
||||
python scripts/cutcrossentropy_install.py --uv | sh && \
|
||||
uv pip install pytest && \
|
||||
uv pip cache purge
|
||||
|
||||
# fix so that git fetch/pull from remote works with shallow clone
|
||||
RUN git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
|
||||
git config --get remote.origin.fetch && \
|
||||
git config --global credential.helper store
|
||||
|
||||
COPY .axolotl-complete.bash /root/.axolotl-complete.bash
|
||||
RUN chmod +x /root/.axolotl-complete.bash && \
|
||||
echo 'source /root/.axolotl-complete.bash' >> ~/.bashrc
|
||||
@@ -6,6 +6,7 @@ ARG TARGETARCH
|
||||
|
||||
FROM nvidia/cuda:$CUDA_VERSION-cudnn$CUDNN_VERSION-devel-ubuntu$UBUNTU_VERSION AS base-builder
|
||||
|
||||
ARG TARGETARCH
|
||||
ARG PYTHON_VERSION="3.11"
|
||||
ARG PYTORCH_VERSION="2.6.0"
|
||||
ARG CUDA="126"
|
||||
@@ -39,28 +40,18 @@ RUN if [ "$TARGETARCH" = "amd64" ]; then \
|
||||
uv pip install "mamba_ssm @ git+https://github.com/state-spaces/mamba.git@main"; \
|
||||
fi
|
||||
|
||||
RUN case "$PYTORCH_VERSION" in \
|
||||
2.9.[0-9]*) \
|
||||
if [ "$TARGETARCH" = "amd64" ]; then \
|
||||
if [ "$CUDA" = "128" ]; then \
|
||||
wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.5.4/flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
|
||||
uv pip install --no-cache-dir flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
|
||||
rm flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
|
||||
elif [ "$CUDA" = "130" ]; then \
|
||||
wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.5.4/flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl; \
|
||||
uv pip install --no-cache-dir flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl; \
|
||||
rm flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl; \
|
||||
fi \
|
||||
elif [ "$TARGETARCH" = "arm64" ]; then \
|
||||
if [ "$CUDA" = "128" ]; then \
|
||||
wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.6.4/flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_aarch64.whl; \
|
||||
uv pip install --no-cache-dir flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_aarch64.whl; \
|
||||
rm flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_aarch64.whl; \
|
||||
elif [ "$CUDA" = "130" ]; then \
|
||||
wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.6.4/flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_aarch64.whl; \
|
||||
uv pip install --no-cache-dir flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_aarch64.whl; \
|
||||
rm flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_aarch64.whl; \
|
||||
fi \
|
||||
fi \
|
||||
;; \
|
||||
esac
|
||||
# Map Python version (e.g., 3.12 -> cp312)
|
||||
RUN PYTHON_CP="cp$(echo $PYTHON_VERSION | tr -d '.')" && \
|
||||
# Map PyTorch version (e.g., 2.9.1 -> torch2.9, 2.10.0 -> torch2.10)
|
||||
TORCH_TAG="torch$(echo $PYTORCH_VERSION | grep -oP '^\d+\.\d+')" && \
|
||||
# Map architecture
|
||||
case "$TARGETARCH" in \
|
||||
amd64) ARCH_TAG="x86_64" ;; \
|
||||
arm64) ARCH_TAG="aarch64" ;; \
|
||||
*) echo "Unsupported architecture: $TARGETARCH"; exit 1 ;; \
|
||||
esac && \
|
||||
WHL_VERSION="v0.7.16" && \
|
||||
WHL_FILE="flash_attn-2.8.3+cu${CUDA}${TORCH_TAG}-${PYTHON_CP}-${PYTHON_CP}-linux_${ARCH_TAG}.whl" && \
|
||||
wget -nv "https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/${WHL_VERSION}/${WHL_FILE}" && \
|
||||
uv pip install --no-cache-dir "${WHL_FILE}" && \
|
||||
rm "${WHL_FILE}"
|
||||
|
||||
Reference in New Issue
Block a user