Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
C
fix(docker): package the gateway's DSML module
Blakea35e30aa9062
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.ymlindex 2565b212..fecc107f 100644--- a/.github/workflows/ci.yml+++ b/.github/workflows/ci.yml@@ -45,6 +45,11 @@ jobs:run: |docker run --rm colibri:ci --versiondocker run --rm colibri:ci --help > /dev/null+ # The gateway has runtime modules that launcher-only commands do not+ # import. Exercise that boundary so the advertised serve path cannot+ # ship with a missing Python file.+ docker run --rm --entrypoint python3 colibri:ci -c \+ "import openai_server; print('gateway imports')"- name: The engine binary is in the image and is executablerun: docker run --rm --entrypoint /app/colibri colibri:ci --help 2>&1 | head -5 || true- name: Lint both Dockerfilesdiff --git a/docker/Dockerfile.slim b/docker/Dockerfile.slimindex 8fa45703..aadb3604 100644--- a/docker/Dockerfile.slim+++ b/docker/Dockerfile.slim@@ -38,7 +38,7 @@ WORKDIR /app# The engine binary plus the launcher and the files it resolves at runtime# (version.py, the gateway, resource planner, doctor, tokenizer headers, tools).COPY --from=build /src/c/colibri ./colibri-COPY c/coli c/version.py c/openai_server.py c/resource_plan.py c/doctor.py c/autotune.py ./+COPY c/coli c/version.py c/openai_server.py c/v4_dsml.py c/resource_plan.py c/doctor.py c/autotune.py ./COPY c/tools/ ./tools/ENV COLI_MODEL=/model \