构建训练镜像

docker build -t registry.example.com/my-train:v1 .
docker push registry.example.com/my-train:v1
tp submit my-custom --profile h200:8 \
  --image registry.example.com/my-train:v1 \
  --observability-url https://wandb.example/my-proj

# syntax=docker/dockerfile:1
ARG BASE_IMAGE=nvidia/cuda:12.8.0-devel-ubuntu24.04
FROM ${BASE_IMAGE}

ARG PYTHON_VERSION=3.12
ENV DEBIAN_FRONTEND=noninteractive \
    HF_HUB_ENABLE_HF_TRANSFER=1

RUN apt-get update && apt-get install -y --no-install-recommends \
        git curl ca-certificates \
    && rm -rf /var/lib/apt/lists/*

COPY --from=ghcr.io/astral-sh/uv:0.8 /uv /usr/local/bin/uv

RUN uv python install ${PYTHON_VERSION} \
 && uv venv --python ${PYTHON_VERSION} /opt/train-venv
ENV VIRTUAL_ENV=/opt/train-venv PATH=/opt/train-venv/bin:$PATH

# 生产上把这些钉住版本。
RUN uv pip install --no-cache \
        torch transformers accelerate trl hf-transfer tuneplane

CMD ["python", "-c", "import torch; print(torch.__version__)"]

docker push registry.example.com/my-train:v1
docker buildx imagetools inspect registry.example.com/my-train:v1   # 读出 digest

tp submit my-custom --profile h200:8 \
  --image registry.example.com/my-train@sha256:abcd… \
  --observability-url https://wandb.example/my-proj

docker run --rm registry.example.com/my-train:v1 \
  python -c "import torch, tuneplane.report; print(torch.__version__)"