refactor: drop the CUDA devel base and fix cold-start failures

.github/workflows/build.yml

@@ -3,9 +3,9 @@ name: build
 # Builds the app image so an orchestrator can pull and run it; amd64 only, since
 # Livepeer GPU work is NVIDIA/amd64.
 #
-# This image is ~25 GB (CUDA devel, torch, TensorRT, ONNX Runtime), so it does not
+# This image is ~15 GB (torch, TensorRT, ONNX Runtime), so it does not
 # fit a GitHub-hosted runner as shipped: the job reclaims disk first, skips the
-# layer cache (a 25 GB image would blow the 10 GB Actions cache anyway), and does
+# layer cache (an image this size would blow the 10 GB Actions cache anyway), and does
 # not run on pull requests, where a build this size buys little for what it costs.
 #
 # GHCR needs no setup (ghcr.io/<owner>/<repo>, public if the repo is). Docker Hub
@@ -32,7 +32,8 @@ jobs:
     steps:
       - uses: actions/checkout@v7
 
-      # A stock runner has roughly 25 GB free, which this image alone exceeds.
+      # A stock runner has roughly 25 GB free, which this image plus its build
+      # layers still crowds.
       # These are preinstalled toolchains the build never touches; dropping them
       # frees about 25 GB more.
       - name: Reclaim disk

Dockerfile

@@ -5,34 +5,47 @@
 # the whole point of the static-registration path — an app needs no SDK, and no
 # awareness of Livepeer at all, to run on the network.
 #
-# NOTE: the fork's own Dockerfile clones the UPSTREAM cumulo-autumn repo, not the
-# fork, so it would not run this rewritten server. We clone the fork at a pinned
-# commit instead.
-FROM nvidia/cuda:12.8.1-cudnn-devel-ubuntu22.04
+# NOTE: the fork's demo/realtime-img2img/Dockerfile clones the UPSTREAM
+# cumulo-autumn repo, not the fork, so it would not run this rewritten server.
+# We clone the fork at a pinned commit instead.
+#
+# Base is python-slim, not nvidia/cuda:*-devel: nothing here compiles against
+# CUDA (torch's cu128 wheels carry the runtime, install-tensorrt is pure pip),
+# and the driver arrives through the container runtime.
+FROM python:3.11-slim
+
+LABEL org.opencontainers.image.title="streamdiffusion-livepeer-runner"
+LABEL org.opencontainers.image.description="daydream's StreamDiffusion realtime-img2img server, packaged unmodified to run as a Livepeer live runner"
+LABEL org.opencontainers.image.source="https://github.com/livepeer/streamdiffusion-livepeer-runner"
+LABEL org.opencontainers.image.licenses="Apache-2.0"
 
 ENV DEBIAN_FRONTEND=noninteractive PYTHONUNBUFFERED=1
 ENV HF_HUB_ENABLE_HF_TRANSFER=1
 
+# git: pip resolves streamdiffusion from the fork, and demo/ is cloned below.
+# libgl1/libglib2.0-0 are opencv's, not CUDA's, so slim needs them either way.
 RUN apt-get update && apt-get install -y --no-install-recommends \
-        software-properties-common ca-certificates curl git \
-    && add-apt-repository ppa:deadsnakes/ppa \
-    && apt-get update && apt-get install -y --no-install-recommends \
-        python3.11 python3.11-venv python3.11-dev \
-    && ln -sf /usr/bin/python3.11 /usr/local/bin/python \
-    && curl -sS https://bootstrap.pypa.io/get-pip.py | python \
-    && python -m pip --version \
+        git libgl1 libglib2.0-0 \
     && apt-get clean && rm -rf /var/lib/apt/lists/*
 
 RUN python -m pip install --no-cache-dir \
         torch==2.7.1+cu128 torchvision==0.22.1+cu128 torchaudio==2.7.1+cu128 \
         --index-url https://download.pytorch.org/whl/cu128
-RUN python -m pip install --no-cache-dir \
-        "streamdiffusion[tensorrt,controlnet,ipadapter] @ git+https://github.com/daydreamlive/StreamDiffusion.git@94b9b96cb8a17d401ffbce516393d6482326ce62"
-RUN apt-get update && apt-get install -y --no-install-recommends \
-        libgl1 libglib2.0-0 \
+# insightface (ipadapter extra) is sdist-only, so it compiles here. Plain g++,
+# nothing CUDA: install for this step only, purge in the same layer.
+RUN apt-get update && apt-get install -y --no-install-recommends build-essential \
+    && python -m pip install --no-cache-dir \
+        "streamdiffusion[tensorrt,controlnet,ipadapter] @ git+https://github.com/daydreamlive/StreamDiffusion.git@94b9b96cb8a17d401ffbce516393d6482326ce62" \
+    && apt-get purge -y --auto-remove build-essential \
     && apt-get clean && rm -rf /var/lib/apt/lists/*
 
-RUN python -m streamdiffusion.tools.install-tensorrt
+ENV LD_LIBRARY_PATH=/usr/local/lib/python3.11/site-packages/nvidia/cuda_runtime/lib:/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib:/usr/local/lib/python3.11/site-packages/nvidia/cublas/lib:/usr/local/lib/python3.11/site-packages/tensorrt_libs
+
+# Pure pip: the tensorrt + cuDNN wheels, polygraphy, onnx-graphsurgeon. polygraphy
+# globs libcudart.so* over LD_LIBRARY_PATH, which on slim is the only place it
+# will find one; the check fails the build rather than the first stream.
+RUN python -m streamdiffusion.tools.install-tensorrt \
+ && python -c "import torch,tensorrt; from polygraphy.cuda.cuda import Cuda; Cuda(); print('ok',torch.__version__,tensorrt.__version__)"
 
 # The pip package doesn't ship the demo/ dir, so clone the fork (pinned) for the server.
 RUN git clone https://github.com/daydreamlive/StreamDiffusion.git /src \
@@ -55,4 +68,6 @@ RUN rm -rf engines && ln -s /models/engines engines
 EXPOSE 7860
 
 # --api-only: skip the built Node frontend (a Livepeer client drives the API directly).
-CMD ["python", "main.py", "--host=0.0.0.0", "--port=7860", "--acceleration=tensorrt", "--api-only"]
+# /models/engines is made at start because the volume masks a build-time mkdir,
+# and mkdir(exist_ok=True) re-raises on the symlink while it dangles.
+CMD ["sh", "-c", "mkdir -p /models/engines && exec python main.py --host=0.0.0.0 --port=7860 --acceleration=tensorrt --api-only"]

README.md

@@ -106,7 +106,7 @@ The price is unchanged by the overlay: static runners advertise it from `runners
 
 CI publishes the image to `ghcr.io/livepeer/streamdiffusion-livepeer-runner` on `main` and `v*` tags. An operator then runs it with a `runners.json` like this repo's, pointed at wherever they run the container, and needs no credentials for a public package.
 
-The image is **~25 GB** (CUDA devel, torch, TensorRT, ONNX Runtime), which is more than a GitHub-hosted runner has free out of the box, so [build.yml](.github/workflows/build.yml) reclaims disk before building and skips the build on pull requests. Building locally is `docker compose build`.
+The image is **~15 GB** (torch, TensorRT, ONNX Runtime), which is still close enough to what a GitHub-hosted runner has free that [build.yml](.github/workflows/build.yml) reclaims disk before building and skips the build on pull requests. Building locally is `docker compose build`.
 
 To publish to Docker Hub as well, set the repository variable `DOCKERHUB_NAMESPACE` and the secrets `DOCKERHUB_USERNAME` and `DOCKERHUB_TOKEN`. GHCR keeps working either way.
 
@@ -119,6 +119,12 @@ uvx pre-commit run --all-files
 
 CI runs the same hooks, checks the compose file parses, and builds the image.
 
+## License and attribution
+
+This repo is an **example** of how to run StreamDiffusion on the [live runner](https://github.com/livepeer/go-livepeer/blob/master/doc/live-runner.md), not a production-ready pipeline. The wrapper here (Dockerfile, [client.py](client.py), the compose files, [runners.json](runners.json)) is MIT, and CI publishing to `ghcr.io/livepeer/` is packaging convenience so an operator can pull it, not a product commitment.
+
+What runs inside the image is daydream's [StreamDiffusion](https://github.com/daydreamlive/StreamDiffusion), itself a fork of [cumulo-autumn/StreamDiffusion](https://github.com/cumulo-autumn/StreamDiffusion). Both are **Apache-2.0**, and this repo builds the fork pinned at `94b9b96` and **unmodified**, so redistribution is permitted and there are no changes to state under section 4(b). The fork ships no `NOTICE` file; its `LICENSE` travels in the image at `/src/LICENSE`. Model weights are downloaded from Hugging Face on first run under their own licenses and are not redistributed here.
+
 ## Building your own
 
 Start from [**template-livepeer-runner**](https://github.com/livepeer/template-livepeer-runner), then list yours in [**runner-app-examples**](https://github.com/livepeer/runner-app-examples#external-examples). That repo also has a minimal example of each transport, mode, registration, and pricing option; the [live runner docs](https://github.com/livepeer/go-livepeer/blob/master/doc/live-runner.md) are the reference.