misc(backend): let's add some more tooling

.github/workflows/build_trtllm.yaml

@@ -50,6 +50,49 @@ jobs:
           install: true
           buildkitd-config: /tmp/buildkitd.toml
 
+      - name: Login to internal Container Registry
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.REGISTRY_USERNAME }}
+          password: ${{ secrets.REGISTRY_PASSWORD }}
+          registry: registry.internal.huggingface.tech
+
+      - name: Login to GitHub Container Registry
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      # If pull request
+      - name: Extract metadata (tags, labels) for Docker
+        if: ${{ github.event_name == 'pull_request' }}
+        id: meta-pr
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            registry.internal.huggingface.tech/api-inference/community/text-generation-inference/tensorrt-llm
+          tags: |
+            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
+
+      # If main, release or tag
+      - name: Extract metadata (tags, labels) for Docker
+        if: ${{ github.event_name != 'pull_request' }}
+        id: meta
+        uses: docker/metadata-action@v4.3.0
+        with:
+          flavor: |
+            latest=auto
+          images: |
+            registry.internal.huggingface.tech/api-inference/community/text-generation-inference/tensorrt-llm
+          #            ghcr.io/huggingface/text-generation-inference
+          tags: |
+            type=semver,pattern={{version}}${{ env.LABEL }}
+            type=semver,pattern={{major}}.{{minor}}${{ env.LABEL }}
+            type=raw,value=latest${{ env.LABEL }},enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
+            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
+
       - name: Build and push Docker image
         id: build-and-push
         env:
@@ -59,7 +102,7 @@ jobs:
           context: .
           file: Dockerfile_trtllm
           target: ci-runtime
-          push: false
+          push: true
           load: true
           platforms: 'linux/amd64'
           build-args: |
@@ -78,5 +121,3 @@ jobs:
 
 
 
-
-

Dockerfile_trtllm

@@ -130,6 +130,7 @@ FROM runtime
 
 LABEL co.huggingface.vendor="Hugging Face Inc."
 LABEL org.opencontainers.image.authors="hardware@hf.co"
+LABEL org.opencontainers.title="Text-Generation-Inference TensorRT-LLM Backend"
 
 ENTRYPOINT ["./text-generation-launcher"]
 CMD ["--executor-worker", "/usr/local/tgi/bin/executorWorker"]
@@ -154,3 +155,9 @@ COPY --from=tgi-builder /usr/local/tgi /usr/local/tgi
 
 # Basically we copy from target/debug instead of target/release
 COPY --from=tgi-builder /usr/src/text-generation-inference/target/debug/text-generation-backends-trtllm /usr/local/tgi/bin/text-generation-launcher
+
+FROM ci-runtime
+
+LABEL co.huggingface.vendor="Hugging Face Inc."
+LABEL org.opencontainers.image.authors="hardware@hf.co"
+LABEL org.opencontainers.title="Text-Generation-Inference TensorRT-LLM Backend CI/CD"

backends/trtllm/CMakeLists.txt

@@ -47,6 +47,7 @@ include(cmake/trtllm.cmake)
 if (CMAKE_BUILD_TYPE STREQUAL "Debug")
     set(TGI_TRTLLM_BACKEND_DEBUG ON)
     add_compile_definitions(TGI_TRTLLM_BACKEND_DEBUG=1)
+    add_compile_definitions(SPDLOG_ACTIVE_LEVEL SPDLOG_LEVEL_TRACE)
 endif ()
 
 if (${TGI_TRTLLM_BACKEND_BUILD_USE_LLD})
@@ -54,13 +55,6 @@ if (${TGI_TRTLLM_BACKEND_BUILD_USE_LLD})
     add_link_options("-fuse-ld=lld")
 endif ()
 
-# This attempt to detect if the compiler can emit warning if it can't apply return value optimization from a function
-check_cxx_compiler_flag("-Wnrvo" COMPILER_SUPPORT_WARNING_ON_NVRO)
-if (${COMPILER_SUPPORT_WARNING_ON_NVRO})
-    message(STATUS "Enabling non-NVRO detection")
-    target_compile_options(tgi_trtllm_backend_impl "-Werror -Wnvro")
-endif ()
-
 # Let's build TRTLLM as part of CMake
 add_subdirectory("${trtllm_SOURCE_DIR}/cpp" "${trtllm_SOURCE_DIR}/..")
 
@@ -97,10 +91,19 @@ if (${TGI_TRTLLM_BACKEND_BUILD_TESTS})
     )
     FetchContent_MakeAvailable(Catch2)
 
+    # This attempt to detect if the compiler can emit warning if it can't apply return value optimization from a function
+    check_cxx_compiler_flag("-Wnrvo" COMPILER_SUPPORT_WARNING_ON_NVRO)
+    if (${COMPILER_SUPPORT_WARNING_ON_NVRO})
+        message(STATUS "Enabling non-NVRO detection")
+        target_compile_options(tgi_trtllm_backend_impl "-Werror -Wnvro")
+    endif ()
+
     cmake_path(GET TRTLLM_NVRTC_WRAPPER_LIBRARY_PATH PARENT_PATH TRTLLM_NVRTC_WRAPPER_PARENT_LIBRARY_PATH)
     message(STATUS "Adding linking path: ${TRTLLM_NVRTC_WRAPPER_PARENT_LIBRARY_PATH}")
 
     add_executable(tgi_trtllm_backend_tests tests/test_hardware.cpp tests/test_backend.cpp)
+
+    target_compile_options(tgi_trtllm_backend_tests PRIVATE -Werror)
     target_link_directories(tgi_trtllm_backend_tests PRIVATE "${TRTLLM_NVRTC_WRAPPER_PARENT_LIBRARY_PATH}")
     target_include_directories(tgi_trtllm_backend_tests PUBLIC "${trtllm_SOURCE_DIR}/cpp/include")
     target_include_directories(tgi_trtllm_backend_tests PUBLIC "csrc/")
@@ -109,9 +112,32 @@ if (${TGI_TRTLLM_BACKEND_BUILD_TESTS})
     target_link_libraries(tgi_trtllm_backend_tests PRIVATE tensorrt_llm nvinfer_plugin_tensorrt_llm tensorrt_llm_nvrtc_wrapper)
 
     if (CMAKE_BUILD_TYPE MATCHES "Debug")
-        set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS}  -fsanitize=address -fsanitize=undefined")
+        if (NOT "${ASan_${CMAKE_C_COMPILER_ID}_FLAGS}" STREQUAL "")
-        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=address -fsanitize=undefined")
+            target_link_options(tgi_trtllm_backend_tests BEFORE PUBLIC -fsanitize=address)
-        target_link_options(tgi_trtllm_backend_tests BEFORE PUBLIC -fsanitize=undefined PUBLIC -fsanitize=address)
+        endif ()
+
+        if (NOT "${UBSan_${CMAKE_C_COMPILER_ID}_FLAGS}" STREQUAL "")
+            target_link_options(tgi_trtllm_backend_tests BEFORE PUBLIC -fsanitize=undefined)
+        endif ()
+
+        if (NOT "${MSan_${CMAKE_C_COMPILER_ID}_FLAGS}" STREQUAL "")
+            target_link_options(tgi_trtllm_backend_tests BEFORE PUBLIC -fsanitize=memory)
+        endif ()
+
+        #        execute_process(COMMAND CMAKE_C_COMPILER --print-file-name=libasan.so OUTPUT_VARIABLE LIBASAN_PATH OUTPUT_STRIP_TRAILING_WHITESPACE RESULT_VARIABLE LIBASAN_FOUND)
+        #        execute_process(COMMAND CMAKE_C_COMPILER --print-file-name=libubsan.so OUTPUT_VARIABLE LIBUBSAN_PATH OUTPUT_STRIP_TRAILING_WHITESPACE RESULT_VARIABLE LIBUBSAN_FOUND)
+
+        #        if (LIBASAN_FOUND)
+        #            set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS}  -fsanitize=address")
+        #            set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=address")
+        #            target_link_options(tgi_trtllm_backend_tests BEFORE PUBLIC -fsanitize=address)
+        #        endif ()
+
+        #        if (LIBUBSAN_FOUND)
+        #            set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS}  -fsanitize=undefined")
+        #            set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=undefined")
+        #            target_link_options(tgi_trtllm_backend_tests BEFORE PUBLIC -fsanitize=undefined)
+        #        endif ()
     endif ()
 
     if(CMAKE_BUILD_TYPE MATCHES "Debug")