[Hardware][IBM Z]Enable v1 for s390x and s390x dockerfile fixes (#22725)

Signed-off-by: Nikhil Suryawanshi <suryawanshin74@gmail.com>

docker/Dockerfile.s390x

@@ -16,7 +16,7 @@ ENV LANG=C.UTF-8 \
 RUN microdnf install -y \
     which procps findutils tar vim git gcc gcc-gfortran g++ make patch zlib-devel \
     libjpeg-turbo-devel libtiff-devel libpng-devel libwebp-devel freetype-devel harfbuzz-devel \
-    openssl-devel openblas openblas-devel autoconf automake libtool cmake numpy && \
+    openssl-devel openblas openblas-devel autoconf automake libtool cmake numpy libsndfile && \
     microdnf clean all
 
 # Python Installation
@@ -136,6 +136,71 @@ RUN --mount=type=cache,target=/root/.cache/uv \
     mkdir -p /tmp/hf-xet/dist && \
     cp dist/*.whl /tmp/hf-xet/dist/
 
+# Build numba
+FROM python-install AS numba-builder
+
+ARG MAX_JOBS
+ARG NUMBA_VERSION=0.61.2
+
+WORKDIR /tmp
+
+# Clone all required dependencies
+RUN --mount=type=cache,target=/root/.cache/uv \
+    microdnf install ninja-build gcc gcc-c++ -y && \
+    git clone --recursive https://github.com/llvm/llvm-project.git -b llvmorg-15.0.7  && \
+    git clone --recursive https://github.com/numba/llvmlite.git -b v0.44.0 && \
+    git clone --recursive https://github.com/numba/numba.git -b ${NUMBA_VERSION} && \
+    cd llvm-project && mkdir build && cd  build && \
+    uv pip install 'cmake<4' setuptools numpy && \
+    export PREFIX=/usr/local && CMAKE_ARGS="${CMAKE_ARGS} -DLLVM_ENABLE_PROJECTS=lld;libunwind;compiler-rt" \
+    CFLAGS="$(echo $CFLAGS | sed 's/-fno-plt //g')" \
+    CXXFLAGS="$(echo $CXXFLAGS | sed 's/-fno-plt //g')" \
+    CMAKE_ARGS="${CMAKE_ARGS} -DFFI_INCLUDE_DIR=$PREFIX/include" \
+    CMAKE_ARGS="${CMAKE_ARGS} -DFFI_LIBRARY_DIR=$PREFIX/lib" \
+    cmake -DCMAKE_INSTALL_PREFIX="${PREFIX}"               \
+        -DCMAKE_BUILD_TYPE=Release                       \
+        -DCMAKE_LIBRARY_PATH="${PREFIX}"                 \
+        -DLLVM_ENABLE_LIBEDIT=OFF                        \
+        -DLLVM_ENABLE_LIBXML2=OFF                        \
+        -DLLVM_ENABLE_RTTI=ON                            \
+        -DLLVM_ENABLE_TERMINFO=OFF                       \
+        -DLLVM_INCLUDE_BENCHMARKS=OFF                    \
+        -DLLVM_INCLUDE_DOCS=OFF                          \
+        -DLLVM_INCLUDE_EXAMPLES=OFF                      \
+        -DLLVM_INCLUDE_GO_TESTS=OFF                      \
+        -DLLVM_INCLUDE_TESTS=OFF                         \
+        -DLLVM_INCLUDE_UTILS=ON                          \
+        -DLLVM_INSTALL_UTILS=ON                          \
+        -DLLVM_UTILS_INSTALL_DIR=libexec/llvm            \
+        -DLLVM_BUILD_LLVM_DYLIB=OFF                      \
+        -DLLVM_LINK_LLVM_DYLIB=OFF                       \
+        -DLLVM_EXPERIMENTAL_TARGETS_TO_BUILD=WebAssembly \
+        -DLLVM_ENABLE_FFI=ON                             \
+        -DLLVM_ENABLE_Z3_SOLVER=OFF                      \
+        -DLLVM_OPTIMIZED_TABLEGEN=ON                     \
+        -DCMAKE_POLICY_DEFAULT_CMP0111=NEW               \
+        -DCOMPILER_RT_BUILD_BUILTINS=ON                  \
+        -DCOMPILER_RT_BUILTINS_HIDE_SYMBOLS=OFF          \
+        -DCOMPILER_RT_BUILD_LIBFUZZER=OFF                \
+        -DCOMPILER_RT_BUILD_CRT=OFF                      \
+        -DCOMPILER_RT_BUILD_MEMPROF=OFF                  \
+        -DCOMPILER_RT_BUILD_PROFILE=OFF                  \
+        -DCOMPILER_RT_BUILD_SANITIZERS=OFF               \
+        -DCOMPILER_RT_BUILD_XRAY=OFF                     \
+        -DCOMPILER_RT_BUILD_GWP_ASAN=OFF                 \
+        -DCOMPILER_RT_BUILD_ORC=OFF                      \
+        -DCOMPILER_RT_INCLUDE_TESTS=OFF                  \
+        ${CMAKE_ARGS} -GNinja ../llvm                    \
+
+    && ninja install  . && \
+    #  build llvmlite
+    cd ../../llvmlite && python setup.py bdist_wheel && \
+    cd ../numba && \
+    if ! grep '#include "dynamic_annotations.h"' numba/_dispatcher.cpp; then \
+       sed -i '/#include "internal\/pycore_atomic.h"/i\#include "dynamic_annotations.h"' numba/_dispatcher.cpp; \
+    fi && python setup.py bdist_wheel
+
+
 # Final build stage
 FROM python-install AS vllm-cpu
 ARG PYTHON_VERSION
@@ -163,23 +228,30 @@ RUN --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,from=torch-vision,source=/tmp/vision/dist,target=/tmp/vision-wheels/ \
     --mount=type=bind,from=hf-xet-builder,source=/tmp/hf-xet/dist,target=/tmp/hf-xet-wheels/ \
     --mount=type=bind,from=torch,source=/tmp/pytorch/dist,target=/tmp/torch-wheels/ \
+    --mount=type=bind,from=numba-builder,source=/tmp/llvmlite/dist,target=/tmp/llvmlite-wheels/ \
+    --mount=type=bind,from=numba-builder,source=/tmp/numba/dist,target=/tmp/numba-wheels/ \
      sed -i '/^torch/d' requirements/build.txt && \
-     ARROW_WHL_FILE=$(ls /tmp/arrow-wheels/pyarrow-*.whl | head -n 1) && \
-     VISION_WHL_FILE=$(ls /tmp/vision-wheels/*.whl | head -n 1) && \
-     HF_XET_WHL_FILE=$(ls /tmp/hf-xet-wheels/*.whl | head -n 1) && \
-     TORCH_WHL_FILE=$(ls /tmp/torch-wheels/*.whl | head -n 1) && \
+     ARROW_WHL_FILE=$(ls /tmp/arrow-wheels/pyarrow-*.whl) && \
+     VISION_WHL_FILE=$(ls /tmp/vision-wheels/*.whl) && \
+     HF_XET_WHL_FILE=$(ls /tmp/hf-xet-wheels/*.whl) && \
+     TORCH_WHL_FILE=$(ls /tmp/torch-wheels/*.whl) && \
+     LLVM_WHL_FILE=$(ls /tmp/llvmlite-wheels/*.whl) && \
+     NUMBA_WHL_FILE=$(ls /tmp/numba-wheels/*.whl) && \
     uv pip install -v \    
         $ARROW_WHL_FILE  \
         $VISION_WHL_FILE \
         $HF_XET_WHL_FILE \
         $TORCH_WHL_FILE \
+        $LLVM_WHL_FILE \
+        $NUMBA_WHL_FILE \
         --index-strategy unsafe-best-match \
         -r requirements/build.txt \
         -r requirements/cpu.txt
 
+
 # Build and install vllm
 RUN --mount=type=cache,target=/root/.cache/uv \
-    VLLM_TARGET_DEVICE=cpu python setup.py bdist_wheel && \
+    VLLM_TARGET_DEVICE=cpu VLLM_CPU_MOE_PREPACK=0 python setup.py bdist_wheel && \
     uv pip install "$(echo dist/*.whl)[tensorizer]"
 
 # setup non-root user for vllm
@@ -196,4 +268,3 @@ WORKDIR /home/vllm
 
 # Set the default entrypoint
 ENTRYPOINT ["python", "-m", "vllm.entrypoints.openai.api_server"]
-

requirements/common.txt

@@ -20,7 +20,8 @@ prometheus-fastapi-instrumentator >= 7.0.0
 tiktoken >= 0.6.0  # Required for DBRX tokenizer
 lm-format-enforcer >= 0.10.11, < 0.11
 llguidance >= 0.7.11, < 0.8.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64"
-outlines_core == 0.2.10
+outlines_core == 0.2.10 ; platform_machine != "s390x"
+outlines == 0.1.11 ; platform_machine == "s390x"
 # required for outlines backend disk cache
 diskcache == 5.6.3
 lark == 1.2.2

requirements/cpu.txt

 # Common dependencies
 -r common.txt
 
-numba == 0.60.0; python_version == '3.9' # v0.61 doesn't support Python 3.9. Required for N-gram speculative decoding
-numba == 0.61.2; python_version > '3.9'
+numba == 0.60.0; python_version == '3.9' and platform_machine != "s390x" # v0.61 doesn't support Python 3.9. Required for N-gram speculative decoding
+numba == 0.61.2; python_version > '3.9' and platform_machine != "s390x"
 
 # Dependencies for CPUs
 packaging>=24.2

vllm/engine/arg_utils.py

@@ -1076,12 +1076,13 @@ class EngineArgs:
         # Set default arguments for V0 or V1 Engine.
         if use_v1:
             self._set_default_args_v1(usage_context, model_config)
-            # Disable chunked prefill for POWER (ppc64le)/ARM CPUs in V1
+            # Disable chunked prefill for POWER (ppc64le)/ARM/s390x CPUs in V1
             if current_platform.is_cpu(
             ) and current_platform.get_cpu_architecture() in (
-                    CpuArchEnum.POWERPC, CpuArchEnum.ARM):
+                    CpuArchEnum.POWERPC, CpuArchEnum.S390X, CpuArchEnum.ARM):
                 logger.info(
-                    "Chunked prefill is not supported for ARM and POWER CPUs; "
+                    "Chunked prefill is not supported for ARM and POWER "
+                    "and S390X CPUs; "
                     "disabling it for V1 backend.")
                 self.enable_chunked_prefill = False
         else:

vllm/platforms/cpu.py

@@ -332,5 +332,6 @@ class CpuPlatform(Platform):
         supplied model configuration.
         """
         arch = cls.get_cpu_architecture()
-        return (cls.supports_v1(model_config) and arch
-                in (CpuArchEnum.X86, CpuArchEnum.POWERPC, CpuArchEnum.ARM))
+        return (cls.supports_v1(model_config)
+                and arch in (CpuArchEnum.X86, CpuArchEnum.POWERPC,
+                             CpuArchEnum.ARM, CpuArchEnum.S390X))

vllm/platforms/interface.py

@@ -81,6 +81,7 @@ class CpuArchEnum(enum.Enum):
     X86 = enum.auto()
     ARM = enum.auto()
     POWERPC = enum.auto()
+    S390X = enum.auto()
     OTHER = enum.auto()
     UNKNOWN = enum.auto()
 
@@ -377,6 +378,8 @@ class Platform:
             return CpuArchEnum.ARM
         elif machine.startswith("ppc"):
             return CpuArchEnum.POWERPC
+        elif machine == "s390x":
+            return CpuArchEnum.S390X
 
         return CpuArchEnum.OTHER if machine else CpuArchEnum.UNKNOWN
 

vllm/v1/worker/cpu_worker.py

@@ -43,8 +43,9 @@ class CPUWorker(Worker):
         # Setup OpenMP threads affinity.
         omp_cpuids = envs.VLLM_CPU_OMP_THREADS_BIND
         if omp_cpuids == "auto" and platform.system() == "Linux":
-            if current_platform.get_cpu_architecture() == CpuArchEnum.POWERPC:
-                # For POWERPC SMT-8/4/2
+            cpu_arch = current_platform.get_cpu_architecture()
+            if cpu_arch in (CpuArchEnum.POWERPC, CpuArchEnum.S390X):
+                # For S390X/POWERPC SMT-8/4/2
                 self.local_omp_cpuid = self._get_autobind_cpu_ids(
                     lambda cpus: [cpu for cpu in cpus if cpu.id % 8 < 4])
             elif current_platform.get_cpu_architecture() == CpuArchEnum.X86: