misc(ci): let's try to build the Dockerfile for trtllm

.github/workflows/build_trtllm.yaml

@@ -43,19 +43,29 @@ jobs:
           aws-region: us-east-1
           role-to-assume: ${{ secrets.AWS_ROLE_GITHUB_TGI_TEST }}
 
-      - name: "Install OS dependencies"
-        run: apt update && apt install -y cmake gcc g++ ninja-build openmpi-devel
-      - name: "Install sccache"
-        run: cargo install sccache --locked
+      - name: Initialize Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          install: true
+          buildkitd-config: /tmp/buildkitd.toml
+
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          file: Dockerfile_trtllm
+          target: runtime
+          push: false
+          platforms: 'linux/amd64'
+          build-args: |
+            BUILD_TYPE=debug
+            SCCACHE_BUCKET: ${{ secrets.AWS_S3_BUCKET_GITHUB_TGI_TEST }}
+            SCCACHE_REGION: "us-east-1"
+            SCCACHE_S3_USE_SSL: false
+            SCCACHE_S3_KEY_PREFIX: "tgi+trtllm"
+            RUSTC_WRAPPER: sccache
 
-      - name: "Build TensorRT-LLM Backend"
-        env:
-          SCCACHE_BUCKET: ${{ secrets.AWS_S3_BUCKET_GITHUB_TGI_TEST }}
-          SCCACHE_REGION: "us-east-1"
-          SCCACHE_S3_USE_SSL: false
-          SCCACHE_S3_KEY_PREFIX: "tgi+trtllm"
-          RUSTC_WRAPPER: sccache
-        run: cargo build --package text-generation-backends-trtllm --bin text-generation-backends-trtllm
 
 
 

Dockerfile_trtllm

@@ -1,13 +1,6 @@
 ARG CUDA_ARCH_LIST="75-real;80-real;86-real;89-real;90-real"
 ARG OMPI_VERSION="4.1.7rc1"
-
-# Build dependencies resolver stage
-FROM lukemathwalker/cargo-chef:latest AS chef
-WORKDIR /usr/src/text-generation-inference/backends/trtllm
-
-FROM chef AS planner
-COPY . .
-RUN cargo chef prepare --recipe-path recipe.json
+ARG BUILD_TYPE=release
 
 # CUDA dependent dependencies resolver stage
 FROM nvidia/cuda:12.6.3-cudnn-devel-ubuntu24.04 AS cuda-builder
@@ -62,18 +55,14 @@ FROM cuda-builder AS tgi-builder
 WORKDIR /usr/src/text-generation-inference
 
 # Install Rust
+ENV PATH="/root/.cargo/bin:$PATH"
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | bash -s -- -y && \
     chmod -R a+w /root/.rustup && \
-    chmod -R a+w /root/.cargo
-
-ENV PATH="/root/.cargo/bin:$PATH"
-RUN cargo install cargo-chef
-
-# Cache dependencies
-COPY --from=planner /usr/src/text-generation-inference/backends/trtllm/recipe.json .
-RUN cargo chef cook --release --recipe-path recipe.json
+    chmod -R a+w /root/.cargo && \
+    cargo install sccache --locked
 
 # Build actual TGI
+ARG BUILD_TYPE
 ARG CUDA_ARCH_LIST
 ENV CMAKE_PREFIX_PATH="/usr/local/mpi:/usr/local/tensorrt:$CMAKE_PREFIX_PATH"
 ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
@@ -83,8 +72,7 @@ COPY . .
 COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
 COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
 RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \
-    cd backends/trtllm && \
-    CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --release
+    CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX sccache build --${BUILD_TYPE} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm
 
 FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime
 RUN apt update && apt install -y libucx0 pipx python3-minimal python3-dev python3-pip python3-venv && \