rocket-inference (sha256:4e22afd0750c2f8df6cda674a89ce47043d37fdf24171c7d2fa1bb56f0e470c8)

Published 2026-10-09 13:11:46 +00:00 by royalcat

Installation

docker pull git.kmsign.org/royalcat/rocket-inference@sha256:4e22afd0750c2f8df6cda674a89ce47043d37fdf24171c7d2fa1bb56f0e470c8
sha256:4e22afd0750c2f8df6cda674a89ce47043d37fdf24171c7d2fa1bb56f0e470c8

Image 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"]
Details
Container
2026-10-09 13:11:46 +00:00
2
2026-10-20 22:33:08 +00:00
OCI / Docker
linux/arm64
41 MiB
Versions (9) View all
e3701a5 2026-10-09
b4634c9 2026-10-09
4a8657b 2026-10-09
b09c082 2026-10-08
64d2fa9 2026-10-08