misc(backend): let's actually cache things now

.github/workflows/build_trtllm.yaml

@@ -33,7 +33,7 @@ jobs:
       - name: Extract TensorRT-LLM version
         run: |
           echo "TENSORRT_LLM_VERSION=$(grep -oP '([a-z,0-9]{40})' $GITHUB_WORKSPACE/backends/trtllm/cmake/trtllm.cmake)" >> $GITHUB_ENV
-          echo "TensorRT-LLM version: $TENSORRT_LLM_VERSION"
+          echo "TensorRT-LLM version: ${{ env.TENSORRT_LLM_VERSION }}"
 
       - name: "Configure AWS Credentials"
         id: aws-creds

Dockerfile_trtllm

@@ -91,13 +91,14 @@ ENV IS_GHA_BUILD ${is_gha_build}
 ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
 ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig:$PKG_CONFIG_PATH"
 ENV USE_LLD_LINKER=ON
+ENV RUSTC_WRAPPER=sccache
 
 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" && \
     python3 backends/trtllm/scripts/setup_sccache.py --is-gha-build ${IS_GHA_BUILD} && \
-    RUSTC_WRAPPER=sccache CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --profile ${build_type} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm && \
+    CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --profile ${build_type} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm && \
     sccache --show-stats
 
 FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime

backends/trtllm/build.rs

@@ -119,7 +119,8 @@ fn build_backend(is_debug: bool, opt_level: &str, out_dir: &PathBuf) -> (PathBuf
 
     if let Some(wrapper) = option_env!("RUSTC_WRAPPER") {
         if wrapper == "sccache" {
-            config.define("CMAKE_CXX_COMPILER_LAUNCHER", "sccache");
+            println!("cargo:warning=Using caching tool: {wrapper}");
+            config.define("CMAKE_CXX_COMPILER_LAUNCHER", wrapper);
         }
     }