Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
docker: the root Dockerfile passes the source commit to the Terminal stage (#3644)
Roberto Jose Etcheverry Romero255861c442ed
diff --git a/.dockerignore b/.dockerignoreindex 4f341af33..2550d9bf6 100644--- a/.dockerignore+++ b/.dockerignore@@ -17,6 +17,11 @@ __pycache__//mtp//models//Strata-data/+# the folders docker/entrypoint.sh creates in a mounted data/ (a link to llama.cpp, the models, the keys): never part of a build (#3644)+/data/install/+/data/state/+/data/home/+/data/Strata-data/third_party/llama.cpp/third_party/*.zip*.donediff --git a/Dockerfile b/Dockerfileindex 82f096cf4..eba34a011 100644--- a/Dockerfile+++ b/Dockerfile@@ -68,6 +68,8 @@ RUN set -e; \# ---- 2. the Terminal (the release archive, built here)FROM ${RUNTIME_BASE} AS terminal+ARG STRATA_COMMIT=+ENV STRATA_BUILD_COMMIT=${STRATA_COMMIT}ENV DEBIAN_FRONTEND=noninteractiveRUN apt-get update && apt-get install -y --no-install-recommends python3 ca-certificates git && rm -rf /var/lib/apt/lists/*COPY . /src/diff --git a/docs/DOCKER.md b/docs/DOCKER.mdindex 81672d749..3ea6f661f 100644--- a/docs/DOCKER.md+++ b/docs/DOCKER.md@@ -296,13 +296,14 @@ to the system or the graphics driver (`packaging/binary_deps.py`); finally it chlibrary inside the finished image. A package that fails any of these stops the build. Nothing is pushed anywhere.`docker/smoke-test.sh` runs the checks we ran on real cards (serves, key, chat, tool call, monitor, clean stop, memory freed, restart); see its first lines for the variables.-**From source.** `docker build -t strata:src .` in the repository compiles the CUDA 13 engine inside Docker, makes the package-and puts it in the same kind of image (`--build-arg CUDA_ARCHITECTURES=89` for one card only, much faster). For a GTX 10, P100 or-V100 build the CUDA 12 variant: `docker build -t strata:src-cuda12 --build-arg CUDA_IMAGE=nvidia/cuda:12.9.1-devel-ubuntu24.04---build-arg CUDA_ARCHITECTURES="60;61;70;75;80;86;89" --build-arg BUILD_VISION=0 .` (the build turns on the Pascal / Volta code by itself-when an architecture below 75 is listed, and names the package `cuda12` with driver 575.51). For AMD and Intel-builds from source see [AMD_HIP.md](AMD_HIP.md) and [INTEL.md](INTEL.md); then package the result with-`packaging/package_engine.py` and use `docker/build.sh`.+**From source.** `docker build -t strata:src --build-arg STRATA_COMMIT=$(git rev-parse HEAD) .` in the repository compiles the CUDA 13+engine inside Docker, makes the package and puts it in the same kind of image (`--build-arg CUDA_ARCHITECTURES=89` for one card only,+much faster). `.git` is not copied into the build, so the commit comes in as `STRATA_COMMIT`; without it the Terminal stage stops.+For a GTX 10, P100 or V100 build the CUDA 12 variant: `docker build -t strata:src-cuda12 --build-arg STRATA_COMMIT=$(git rev-parse HEAD)+--build-arg CUDA_IMAGE=nvidia/cuda:12.9.1-devel-ubuntu24.04 --build-arg CUDA_ARCHITECTURES="60;61;70;75;80;86;89" --build-arg BUILD_VISION=0 .`+(the build turns on the Pascal / Volta code by itself when an architecture below 75 is listed, and names the package `cuda12` with+driver 575.51). For AMD and Intel builds from source see [AMD_HIP.md](AMD_HIP.md) and [INTEL.md](INTEL.md); then package the result+with `packaging/package_engine.py` and use `docker/build.sh`.## Publishing the images (for maintainers)