[CI/Build][CPU] Enable cross compilation in CPU release pipeline (#20423)

Signed-off-by: jiang1.li <jiang1.li@intel.com>

.buildkite/release-pipeline.yaml

@@ -101,7 +101,7 @@ steps:
       queue: cpu_queue_postmerge
     commands:
       - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version) --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest --progress plain --target vllm-openai -f docker/Dockerfile.cpu ."
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --build-arg VLLM_CPU_AVX512BF16=true --build-arg VLLM_CPU_AVX512VNNI=true --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version) --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest --progress plain --target vllm-openai -f docker/Dockerfile.cpu ."
       - "docker push public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest"
       - "docker push public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version)"
     env:

cmake/cpu_extension.cmake

@@ -12,9 +12,8 @@ endif()
 #
 # Define environment variables for special configurations
 #
-if(DEFINED ENV{VLLM_CPU_AVX512BF16})
-    set(ENABLE_AVX512BF16 ON)
-endif()
+set(ENABLE_AVX512BF16 $ENV{VLLM_CPU_AVX512BF16})
+set(ENABLE_AVX512VNNI $ENV{VLLM_CPU_AVX512VNNI})
 
 include_directories("${CMAKE_SOURCE_DIR}/csrc")
 
@@ -107,10 +106,19 @@ if (AVX512_FOUND AND NOT AVX512_DISABLED)
     endif()
 
     find_isa(${CPUINFO} "avx512_vnni" AVX512VNNI_FOUND)
-    if (AVX512VNNI_FOUND)
-        list(APPEND CXX_COMPILE_FLAGS "-mavx512vnni")
-        set(ENABLE_AVX512VNNI ON) 
-    endif() 
+    if (AVX512VNNI_FOUND OR ENABLE_AVX512VNNI)
+        if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU" AND
+            CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 12.3)
+            list(APPEND CXX_COMPILE_FLAGS "-mavx512vnni")
+            set(ENABLE_AVX512VNNI ON)
+        else()
+            set(ENABLE_AVX512VNNI OFF)
+            message(WARNING "Disable AVX512-VNNI ISA support, requires gcc/g++ >= 12.3")
+        endif()
+    else()
+        set(ENABLE_AVX512VNNI OFF)
+        message(WARNING "Disable AVX512-VNNI ISA support, no avx512_vnni found in local CPU flags." " If cross-compilation is required, please set env VLLM_CPU_AVX512VNNI=1.")
+    endif()
     
 elseif (AVX2_FOUND)
     list(APPEND CXX_COMPILE_FLAGS "-mavx2")
@@ -257,6 +265,8 @@ elseif(POWER10_FOUND)
         ${VLLM_EXT_SRC})
 endif()
 
+message(STATUS "CPU extension source files: ${VLLM_EXT_SRC}")
+
 #
 # Define extension targets
 #

docker/Dockerfile.cpu

@@ -8,6 +8,8 @@
 # Build arguments:
 #   PYTHON_VERSION=3.12 (default)|3.11|3.10|3.9
 #   VLLM_CPU_DISABLE_AVX512=false (default)|true
+#   VLLM_CPU_AVX512BF16=false (default)|true
+#   VLLM_CPU_AVX512VNNI=false (default)|true
 #
 
 ######################### BASE IMAGE #########################
@@ -60,8 +62,14 @@ FROM base AS vllm-build
 
 ARG GIT_REPO_CHECK=0
 # Support for building with non-AVX512 vLLM: docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" ...
-ARG VLLM_CPU_DISABLE_AVX512
+ARG VLLM_CPU_DISABLE_AVX512=0
 ENV VLLM_CPU_DISABLE_AVX512=${VLLM_CPU_DISABLE_AVX512}
+# Support for building with AVX512BF16 ISA: docker build --build-arg VLLM_CPU_AVX512BF16="true" ...
+ARG VLLM_CPU_AVX512BF16=0
+ENV VLLM_CPU_AVX512BF16=${VLLM_CPU_AVX512BF16}
+# Support for building with AVX512VNNI ISA: docker build --build-arg VLLM_CPU_AVX512VNNI="true" ...
+ARG VLLM_CPU_AVX512VNNI=0
+ENV VLLM_CPU_AVX512VNNI=${VLLM_CPU_AVX512VNNI}
 
 WORKDIR /workspace/vllm