Support CPU inference with VSX PowerPC ISA (#5652)

Dockerfile.ppc64le

@@ -0,0 +1,22 @@
+FROM mambaorg/micromamba
+ARG MAMBA_DOCKERFILE_ACTIVATE=1
+USER root
+
+RUN apt-get update  -y     && apt-get install -y git wget vim numactl gcc-12 g++-12 protobuf-compiler libprotobuf-dev     && update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12
+
+# Some packages in requirements-cpu are installed here
+# IBM provides optimized packages for ppc64le processors in the open-ce project for mamba
+# Currently these may not be available for venv or pip directly
+RUN micromamba install -y -n base -c https://ftp.osuosl.org/pub/open-ce/1.11.0-p10/ -c defaults     python=3.10     pytorch-cpu=2.1.2     torchvision-cpu=0.16.2    &&     micromamba clean --all --yes
+
+COPY ./ /workspace/vllm
+
+WORKDIR /workspace/vllm
+
+# These packages will be in rocketce eventually
+RUN pip install -v -r requirements-cpu.txt --prefer-binary --extra-index-url https://repo.fury.io/mgiessing
+
+RUN VLLM_TARGET_DEVICE=cpu python3 setup.py install
+
+WORKDIR /vllm-workspace
+ENTRYPOINT ["/opt/conda/bin/python3", "-m", "vllm.entrypoints.openai.api_server"]

cmake/cpu_extension.cmake

@@ -46,6 +46,8 @@ is_avx512_disabled(AVX512_DISABLED)
 
 find_isa(${CPUINFO} "avx2" AVX2_FOUND)
 find_isa(${CPUINFO} "avx512f" AVX512_FOUND)
+find_isa(${CPUINFO} "POWER10" POWER10_FOUND)
+find_isa(${CPUINFO} "POWER9" POWER9_FOUND)
 
 if (AVX512_FOUND AND NOT AVX512_DISABLED)
     list(APPEND CXX_COMPILE_FLAGS
@@ -68,8 +70,15 @@ if (AVX512_FOUND AND NOT AVX512_DISABLED)
 elseif (AVX2_FOUND)
     list(APPEND CXX_COMPILE_FLAGS "-mavx2")
     message(WARNING "vLLM CPU backend using AVX2 ISA")
+elseif (POWER9_FOUND OR POWER10_FOUND)
+    message(STATUS "PowerPC detected")
+    # Check for PowerPC VSX support
+    list(APPEND CXX_COMPILE_FLAGS
+        "-mvsx"
+        "-mcpu=native"
+        "-mtune=native")
 else()
-    message(FATAL_ERROR "vLLM CPU backend requires AVX512 or AVX2 ISA support.")
+    message(FATAL_ERROR "vLLM CPU backend requires AVX512 or AVX2 or Power9+ ISA support.")
 endif()
 
 message(STATUS "CPU extension compile flags: ${CXX_COMPILE_FLAGS}")