ci: use tei 1.4.0 with gdbserver

Dockerfile-cuda

@@ -1,128 +1,9 @@
-FROM nvidia/cuda:12.2.0-devel-ubuntu22.04 AS base-builder
-
-ENV SCCACHE=0.5.4
-ENV RUSTC_WRAPPER=/usr/local/bin/sccache
-ENV PATH="/root/.cargo/bin:${PATH}"
-
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
-    curl \
-    libssl-dev \
-    pkg-config \
-    && rm -rf /var/lib/apt/lists/*
-
-# Donwload and configure sccache
-RUN curl -fsSL https://github.com/mozilla/sccache/releases/download/v$SCCACHE/sccache-v$SCCACHE-x86_64-unknown-linux-musl.tar.gz | tar -xzv --strip-components=1 -C /usr/local/bin sccache-v$SCCACHE-x86_64-unknown-linux-musl/sccache && \
-    chmod +x /usr/local/bin/sccache
-
-RUN curl https://sh.rustup.rs -sSf | bash -s -- -y
-RUN cargo install cargo-chef --locked
-
-FROM base-builder AS planner
-
-WORKDIR /usr/src
-
-COPY backends backends
-COPY core core
-COPY router router
-COPY Cargo.toml ./
-COPY Cargo.lock ./
-
-RUN cargo chef prepare  --recipe-path recipe.json
-
-FROM base-builder AS builder
-
-ARG CUDA_COMPUTE_CAP=80
-ARG GIT_SHA
-ARG DOCKER_LABEL
-
-# Limit parallelism
-ARG RAYON_NUM_THREADS
-ARG CARGO_BUILD_JOBS
-ARG CARGO_BUILD_INCREMENTAL
-
-# sccache specific variables
-ARG ACTIONS_CACHE_URL
-ARG ACTIONS_RUNTIME_TOKEN
-ARG SCCACHE_GHA_ENABLED
-
-WORKDIR /usr/src
-
-RUN if [ ${CUDA_COMPUTE_CAP} -ge 75 -a ${CUDA_COMPUTE_CAP} -lt 80 ]; \
-    then  \
-        nvprune --generate-code code=sm_${CUDA_COMPUTE_CAP} /usr/local/cuda/lib64/libcublas_static.a -o /usr/local/cuda/lib64/libcublas_static.a; \
-    elif [ ${CUDA_COMPUTE_CAP} -ge 80 -a ${CUDA_COMPUTE_CAP} -lt 90 ]; \
-    then  \
-        nvprune --generate-code code=sm_80 --generate-code code=sm_${CUDA_COMPUTE_CAP} /usr/local/cuda/lib64/libcublas_static.a -o /usr/local/cuda/lib64/libcublas_static.a; \
-    elif [ ${CUDA_COMPUTE_CAP} -eq 90 ]; \
-    then  \
-        nvprune --generate-code code=sm_90 /usr/local/cuda/lib64/libcublas_static.a -o /usr/local/cuda/lib64/libcublas_static.a; \
-    else  \
-        echo "cuda compute cap ${CUDA_COMPUTE_CAP} is not supported"; exit 1; \
-    fi;
-
-COPY --from=planner /usr/src/recipe.json recipe.json
-
-RUN if [ ${CUDA_COMPUTE_CAP} -ge 75 -a ${CUDA_COMPUTE_CAP} -lt 80 ]; \
-    then \
-        cargo chef cook  --features candle-cuda-turing --features static-linking --no-default-features --recipe-path recipe.json && sccache -s; \
-    else \
-        cargo chef cook  --features candle-cuda --features static-linking --no-default-features --recipe-path recipe.json && sccache -s; \
-    fi;
-
-COPY backends backends
-COPY core core
-COPY router router
-COPY Cargo.toml ./
-COPY Cargo.lock ./
-
-FROM builder AS http-builder
-
-RUN if [ ${CUDA_COMPUTE_CAP} -ge 75 -a ${CUDA_COMPUTE_CAP} -lt 80 ]; \
-    then \
-        cargo build  --bin text-embeddings-router -F candle-cuda-turing -F static-linking -F http --no-default-features && sccache -s; \
-    else \
-        cargo build  --bin text-embeddings-router -F candle-cuda -F static-linking -F http --no-default-features && sccache -s; \
-    fi;
-
-FROM builder AS grpc-builder
+FROM ghcr.io/huggingface/text-embeddings-inference:1.4.0 AS debugee
 
 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
-    unzip \
-    && rm -rf /var/lib/apt/lists/*
-
-RUN PROTOC_ZIP=protoc-21.12-linux-x86_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 if [ ${CUDA_COMPUTE_CAP} -ge 75 -a ${CUDA_COMPUTE_CAP} -lt 80 ]; \
-    then \
-        cargo build  --bin text-embeddings-router -F candle-cuda-turing -F static-linking -F grpc --no-default-features && sccache -s; \
-    else \
-        cargo build  --bin text-embeddings-router -F candle-cuda -F static-linking -F grpc --no-default-features && sccache -s; \
-    fi;
-
-FROM nvidia/cuda:12.2.0-base-ubuntu22.04 AS base
-
-ARG DEFAULT_USE_FLASH_ATTENTION=True
-
-ENV HUGGINGFACE_HUB_CACHE=/data \
-    PORT=80 \
-    USE_FLASH_ATTENTION=$DEFAULT_USE_FLASH_ATTENTION
-
-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
-
-COPY --from=http-builder /usr/src/target/release/text-embeddings-router /usr/local/bin/text-embeddings-router
+    gdb \
+    procps \
+    binutils &&
+    rm -rf /var/lib/apt/lists/*
 
-ENTRYPOINT ["text-embeddings-router"]
-CMD ["--json-output"]
+ENTRYPOINT ["gdbserver", "0.0.0.0:9000", "text-embeddings-router", "--json-output"]