Add Dockerfile for ARM64 architecture support and update README instructions

Dockerfile-arm64

@@ -0,0 +1,87 @@
+FROM lukemathwalker/cargo-chef:latest-rust-1.92-bookworm AS chef
+WORKDIR /usr/src
+
+ENV SCCACHE=0.10.0
+ENV RUSTC_WRAPPER=/usr/local/bin/sccache
+
+# Download and configure ARM64-compatible sccache
+RUN curl -fsSL https://github.com/mozilla/sccache/releases/download/v$SCCACHE/sccache-v$SCCACHE-aarch64-unknown-linux-musl.tar.gz | tar -xzv --strip-components=1 -C /usr/local/bin sccache-v$SCCACHE-aarch64-unknown-linux-musl/sccache && \
+    chmod +x /usr/local/bin/sccache
+
+FROM chef AS planner
+
+COPY backends backends
+COPY core core
+COPY router router
+COPY Cargo.toml ./
+COPY Cargo.lock ./
+
+RUN cargo chef prepare  --recipe-path recipe.json
+
+FROM chef AS builder
+
+ARG GIT_SHA
+ARG DOCKER_LABEL
+
+# sccache specific variables
+ARG SCCACHE_GHA_ENABLED
+
+COPY --from=planner /usr/src/recipe.json recipe.json
+
+RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \
+    --mount=type=secret,id=actions_runtime_token,env=ACTIONS_RUNTIME_TOKEN \
+    cargo chef cook --release --features ort,candle,static-linking --no-default-features --recipe-path recipe.json && sccache -s
+
+COPY backends backends
+COPY core core
+COPY router router
+COPY Cargo.toml ./
+COPY Cargo.lock ./
+
+FROM builder AS http-builder
+
+RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \
+    --mount=type=secret,id=actions_runtime_token,env=ACTIONS_RUNTIME_TOKEN \
+    cargo build --release --bin text-embeddings-router --features ort,candle,static-linking,http --no-default-features && sccache -s
+
+FROM builder AS grpc-builder
+
+RUN PROTOC_ZIP=protoc-21.12-linux-aarch_64.zip && \
+    curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP && \
+    unzip -o $PROTOC_ZIP -d /usr/local bin/protoc && \
+    unzip -o $PROTOC_ZIP -d /usr/local 'include/*' && \
+    rm -f $PROTOC_ZIP
+
+COPY proto proto
+
+RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \
+    --mount=type=secret,id=actions_runtime_token,env=ACTIONS_RUNTIME_TOKEN \
+    cargo build --release --bin text-embeddings-router --features ort,candle,static-linking,grpc --no-default-features && sccache -s
+
+FROM debian:bookworm-slim AS base
+
+ENV HUGGINGFACE_HUB_CACHE=/data \
+    PORT=80 \
+    RAYON_NUM_THREADS=8 \
+    LD_LIBRARY_PATH=/usr/local/lib
+
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+    libomp-dev \
+    ca-certificates \
+    libssl-dev \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+FROM base AS grpc
+
+COPY --from=grpc-builder /usr/src/target/release/text-embeddings-router /usr/local/bin/text-embeddings-router
+
+ENTRYPOINT ["text-embeddings-router"]
+CMD ["--json-output"]
+
+FROM base AS http
+
+COPY --from=http-builder /usr/src/target/release/text-embeddings-router /usr/local/bin/text-embeddings-router
+
+ENTRYPOINT ["text-embeddings-router"]
+CMD ["--json-output"]

README.md

@@ -604,7 +604,7 @@ supported via Docker. As such inference will be CPU bound and most likely pretty
 M1/M2 ARM CPU.
 
 ```
-docker build . -f Dockerfile --platform=linux/arm64
+docker build . -f Dockerfile-arm64 --platform=linux/arm64
 ```
 
 ## Examples