misc(backend): add more info

.github/workflows/build_trtllm.yaml

@@ -30,12 +30,18 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
+      - name: Extract TensorRT-LLM version
+        run: |
+          echo "TENSORRT_LLM_VERSION=$(grep -oP '([a-z,0-9]{40})' backends/trtllm/cmake/trtllm.cmake)" >> $GITHUB_ENV
+          echo "TensorRT-LLM version: ${{ env.TENSORRT_LLM_VERSION }}"
+
       - name: "Configure AWS Credentials"
         id: aws-creds
         uses: aws-actions/configure-aws-credentials@v4
         with:
           aws-region: us-east-1
           role-to-assume: ${{ secrets.AWS_ROLE_GITHUB_TGI_TEST }}
+          role-duration-seconds: 7200
           output-credentials: true
 
       - name: Initialize Docker Buildx
@@ -59,18 +65,15 @@ jobs:
           build-args: |
             BUILD_TYPE=dev
             IS_GHA_BUILD=true
-            SCCACHE_LOG=debug
-            SCCACHE_NO_DAEMON=1
-            SCCACHE_S3_USE_SSL: false
-            SCCACHE_S3_KEY_PREFIX: trtllm
           secrets: |
             aws_access_key_id=${{ steps.aws-creds.outputs.aws-access-key-id }}
             aws_secret_access_key=${{ steps.aws-creds.outputs.aws-secret-access-key }}
             aws_session_token=${{ steps.aws-creds.outputs.aws-session-token }}
             sccache_s3_bucket=${{ secrets.AWS_S3_BUCKET_GITHUB_TGI_TEST }}
+            sccache_s3_key_prefix="trtllm-${{ env.TENSORRT_LLM_VERSION }}"
             sccache_s3_region=us-east-1
-          cache-from: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
+          cache-from: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }}-trtllm,mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
-          cache-to: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
+          cache-to: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }}-trtllm,mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
 
 
 

Dockerfile_trtllm

@@ -66,10 +66,12 @@ RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | bash -s -- -y &&
 ARG BUILD_TYPE
 ARG CUDA_ARCH_LIST
 ARG IS_GHA_BUILD
+ARG SCCACHE_S3_KEY_PREFIX
+
+ENV IS_GHA_BUILD=${IS_GHA_BUILD}
 ENV CMAKE_PREFIX_PATH="/usr/local/mpi:/usr/local/tensorrt:$CMAKE_PREFIX_PATH"
 ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
 ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig:$PKG_CONFIG_PATH"
-ENV SCCACHE_GHA_ENABLED=${IS_GHA_BUILD}
 
 COPY . .
 COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
@@ -78,8 +80,8 @@ RUN --mount=type=secret,id=aws_access_key_id,env=AWS_ACCESS_KEY_ID  \
     --mount=type=secret,id=aws_secret_access_key,env=AWS_SECRET_ACCESS_KEY \
     --mount=type=secret,id=aws_session_token,env=AWS_SESSION_TOKEN \
     --mount=type=secret,id=sccache_s3_bucket,env=SCCACHE_BUCKET \
+    --mount=type=secret,id=sccache_s3_key_prefix,env=SCCACHE_S3_KEY_PREFIX \
     --mount=type=secret,id=sccache_s3_region,env=SCCACHE_REGION \
-    echo "AWS_ACCESS_KEY_ID: ${AWS_ACCESS_KEY_ID}" && \
     mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \
     RUSTC_WRAPPER=sccache CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --profile ${BUILD_TYPE} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm