rocket-inference (sha256:66440719c68757db9db505e314eb3c0692cf54a20814dd881b6ef6c9a53f6954)
Published 2026-10-07 22:05:09 +00:00 by royalcat
Installation
docker pull git.kmsign.org/royalcat/rocket-inference@sha256:66440719c68757db9db505e314eb3c0692cf54a20814dd881b6ef6c9a53f6954sha256:66440719c68757db9db505e314eb3c0692cf54a20814dd881b6ef6c9a53f6954Image layers
| # debian.sh --arch 'arm64' out/ 'trixie' '@1791158400' |
| RUN /bin/sh -c apt-get update && apt-get install -y --no-install-recommends curl ca-certificates && rm -rf /var/lib/apt/lists/* # buildkit |
| COPY /src/target/aarch64-unknown-linux-gnu/release/rocket-inference /usr/local/bin/rocket-inference # buildkit |
| EXPOSE [8383/tcp] |
| ENTRYPOINT ["rocket-inference"] |
| CMD ["serve" "--backend" "flex" "--dtype" "f32" "--npu" "--npu-attn" "cpu" "--port" "8383" "--max-tokens" "8192" "--model-dir" "/models/qwen3-embedding-0.6b" "--model-name" "qwen3-embedding"] |