mirror of
https://github.com/axolotl-ai-cloud/axolotl.git
synced 2026-10-12 02:11:20 +00:00
* Upgrade to torch 2.14.1 for CI and cloud images * stay on 2.14.x in pyproject.toml * restore longer steps for muon convergence
52 lines
1.8 KiB
Plaintext
52 lines
1.8 KiB
Plaintext
# syntax=docker/dockerfile:1
|
|
ARG CUDA_VERSION="13.0.3"
|
|
ARG CUDNN_VERSION=""
|
|
ARG UBUNTU_VERSION="22.04"
|
|
ARG MAX_JOBS=4
|
|
ARG TARGETARCH
|
|
|
|
FROM nvidia/cuda:$CUDA_VERSION-cudnn$CUDNN_VERSION-devel-ubuntu$UBUNTU_VERSION AS base-builder
|
|
|
|
ARG TARGETARCH
|
|
ARG PYTHON_VERSION="3.14"
|
|
ARG PYTORCH_VERSION="2.14.1"
|
|
ARG CUDA="130"
|
|
ARG TORCH_BACKEND="cu130"
|
|
ARG TORCH_INDEX_URL=""
|
|
ARG TORCH_CUDA_ARCH_LIST="9.0 10.0 10.3 12.0+PTX"
|
|
|
|
ENV PYTHON_VERSION=$PYTHON_VERSION
|
|
ENV TORCH_CUDA_ARCH_LIST=$TORCH_CUDA_ARCH_LIST
|
|
|
|
RUN apt-get update \
|
|
&& apt-get install -y wget git build-essential ninja-build git-lfs libaio-dev pkg-config curl \
|
|
&& apt-get install -y --allow-change-held-packages vim curl nano zstd libnccl2 libnccl-dev ibverbs-providers ibverbs-utils infiniband-diags librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm rsync s3fs \
|
|
&& rm -rf /var/cache/apt/archives \
|
|
&& rm -rf /var/lib/apt/lists/* \
|
|
&& git lfs install --skip-repo \
|
|
&& curl -LsSf https://astral.sh/uv/install.sh | sh
|
|
|
|
ENV PATH="/root/.local/bin:${PATH}"
|
|
|
|
RUN uv python install ${PYTHON_VERSION}
|
|
|
|
WORKDIR /workspace
|
|
|
|
RUN uv venv --no-project --relocatable axolotl-venv
|
|
|
|
ENV PATH="/workspace/axolotl-venv/bin:${PATH}"
|
|
|
|
RUN --mount=type=cache,target=/root/.cache/uv \
|
|
uv pip install packaging setuptools wheel psutil \
|
|
&& if [ -n "$TORCH_INDEX_URL" ]; then \
|
|
uv pip install --index-url "$TORCH_INDEX_URL" torch==${PYTORCH_VERSION} torchvision; \
|
|
else \
|
|
UV_TORCH_BACKEND=$TORCH_BACKEND uv pip install torch==${PYTORCH_VERSION} torchvision; \
|
|
fi \
|
|
&& uv pip install awscli pydantic
|
|
|
|
RUN --mount=type=cache,target=/root/.cache/uv \
|
|
if [ "$TARGETARCH" = "amd64" ]; then \
|
|
MAMBA_SKIP_CUDA_BUILD=TRUE CAUSAL_CONV1D_SKIP_CUDA_BUILD=TRUE uv pip install --no-build-isolation mamba_ssm causal_conv1d; \
|
|
fi
|