vh
5bbf0aaeba
Contract, service and tests (fake engine, no GPU). Scores through the checkpoint's own inference.py (DecisionEngine.predict, sha256-pinned); maps semif decisions onto Jev choice questions, packs /decide/shared into calls of at most 16, runs orderings in waves, and keeps semif's error mapping, admission, body limit and hard VRAM cap. Deltas from semif-serve are listed in the contract.
52 lines
2.6 KiB
Docker
52 lines
2.6 KiB
Docker
# syntax=docker/dockerfile:1
|
|
# intern-decision-serve: Intern-Decision-4B, scored by the checkpoint's own inference.py, behind
|
|
# semif-serve's HTTP surface. Contract: intern-decision-serve.contract.md.
|
|
# docker build -t intern-decision-serve:<version> .
|
|
# Weights AND inference.py are NOT in the image: both are read from the mounted HF cache at the
|
|
# pinned revision, offline (INV-5); inference.py's sha256 is checked before it is imported (INV-3).
|
|
|
|
# The dependency manifest with the service's own version blanked to 0.0.0, so a version bump
|
|
# leaves these two files byte-identical and the ~4 GB torch/CUDA layer below stays cached.
|
|
FROM python:3.12-slim-bookworm AS deps
|
|
WORKDIR /deps
|
|
COPY pyproject.toml uv.lock ./
|
|
RUN python - <<'PY'
|
|
import re, pathlib
|
|
p = pathlib.Path("pyproject.toml")
|
|
p.write_text(re.sub(r'(?m)^version = "[^"]+"', 'version = "0.0.0"', p.read_text(), count=1))
|
|
l = pathlib.Path("uv.lock")
|
|
l.write_text(re.sub(r'(name = "intern-decision-serve"\nversion = )"[^"]+"', r'\1"0.0.0"', l.read_text(), count=1))
|
|
PY
|
|
|
|
FROM python:3.12-slim-bookworm
|
|
# The model plus Qwen3.5's fast kernels (fla + causal-conv1d): the bench stack.
|
|
ARG EXTRAS="--extra model --extra fast"
|
|
COPY --from=ghcr.io/astral-sh/uv:0.6.9 /uv /bin/uv
|
|
ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy UV_PYTHON_DOWNLOADS=never
|
|
# The fast extra needs a C compiler AT RUNTIME: triton builds its CUDA driver shim on first use,
|
|
# and without gcc the warm-up dies with "Failed to find C compiler" (semif-serve, 2026-09-27).
|
|
RUN apt-get update && apt-get install -y --no-install-recommends ca-certificates \
|
|
&& if echo "$EXTRAS" | grep -q -- '--extra fast'; then \
|
|
apt-get install -y --no-install-recommends gcc libc6-dev; fi \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
WORKDIR /app
|
|
COPY --from=deps /deps/pyproject.toml /deps/uv.lock ./
|
|
RUN --mount=type=cache,target=/root/.cache/uv \
|
|
uv sync --frozen --no-dev $EXTRAS --no-install-project
|
|
COPY pyproject.toml uv.lock ./
|
|
COPY src ./src
|
|
RUN uv sync --frozen --no-dev $EXTRAS --no-editable --no-cache
|
|
RUN groupadd --system --gid 10001 intern \
|
|
&& useradd --system --uid 10001 --gid 10001 --no-create-home --shell /usr/sbin/nologin intern
|
|
USER intern
|
|
ENV PATH=/app/.venv/bin:$PATH \
|
|
HF_HOME=/hf \
|
|
HF_HUB_OFFLINE=1 \
|
|
TRANSFORMERS_OFFLINE=1 \
|
|
HF_HUB_DISABLE_TELEMETRY=1 \
|
|
TRITON_CACHE_DIR=/tmp/triton-cache \
|
|
NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
|
EXPOSE 8000
|
|
# One worker (INV-2): the model and the inference lock live in this one process.
|
|
CMD ["uvicorn", "intern_decision_serve.main:app_from_env", "--factory", "--host", "0.0.0.0", "--port", "8000", "--workers", "1"]
|