Fix: Build error seen on Power Architecture (#10421)

Signed-off-by: Manjul Mohan <manjul.mohan@ibm.com>
Signed-off-by: B-201 <Joy25810@foxmail.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: ismael-dm <ismaeldm99@gmail.com>
Signed-off-by: Andrew Nesbitt <andrewnez@gmail.com>
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: yan ma <yan.ma@intel.com>
Signed-off-by: Angus Wang <wangjadehao@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: rickyx <rickyx@anyscale.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
Co-authored-by: Manjul Mohan manjul.mohan@ibm.com <manjulmohan@ltcd97-lp2.aus.stglabs.ibm.com>
Co-authored-by: B-201 <Joy25810@foxmail.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: ismael-dm <ismaeldm99@gmail.com>
Co-authored-by: Andrew Nesbitt <andrewnez@gmail.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: Yan Ma <yan.ma@intel.com>
Co-authored-by: Angus Wang <wangjadehao@gmail.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Ricky Xu <rickyx@anyscale.com>
Co-authored-by: Kevin H. Luu <kevin@anyscale.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: Travis Johnson <tsjohnso@us.ibm.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>

cmake/cpu_extension.cmake

@@ -16,10 +16,16 @@ include_directories("${CMAKE_SOURCE_DIR}/csrc")
 #
 # Check the compile flags
 #
-list(APPEND CXX_COMPILE_FLAGS
+if (CMAKE_SYSTEM_PROCESSOR STREQUAL "ppc64le")
+    list(APPEND CXX_COMPILE_FLAGS
+        "-fopenmp"
+        "-DVLLM_CPU_EXTENSION")
+else()
+    list(APPEND CXX_COMPILE_FLAGS
         "-fopenmp"
         "-mf16c"
         "-DVLLM_CPU_EXTENSION")
+endif()
 
 execute_process(COMMAND cat /proc/cpuinfo
                 RESULT_VARIABLE CPUINFO_RET

csrc/cpu/attention.cpp

@@ -24,12 +24,20 @@ struct KernelVecType<float> {
 
 template <>
 struct KernelVecType<c10::Half> {
+#ifdef __powerpc64__
+  // Power architecture-specific vector types
+  using q_load_vec_type = vec_op::FP32Vec8;
+  using k_load_vec_type = vec_op::FP32Vec16;
+  using v_load_vec_type = vec_op::FP32Vec16;
+#else
+  // Fallback for other architectures, including x86
   using q_load_vec_type = vec_op::FP16Vec8;
-  using q_vec_type = vec_op::FP32Vec16;
   using k_load_vec_type = vec_op::FP16Vec16;
+  using v_load_vec_type = vec_op::FP16Vec16;
+#endif
+  using q_vec_type = vec_op::FP32Vec16;
   using k_vec_type = vec_op::FP32Vec16;
   using qk_acc_vec_type = vec_op::FP32Vec16;
-  using v_load_vec_type = vec_op::FP16Vec16;
 };
 
 #ifdef __AVX512BF16__

csrc/cpu/quant.cpp

@@ -25,7 +25,13 @@ struct KernelVecType<c10::BFloat16> {
 
 template <>
 struct KernelVecType<c10::Half> {
+#ifdef __powerpc64__
+  // Power architecture-specific vector type
+  using load_vec_type = vec_op::FP32Vec16;
+#else
+  // Fallback for other architectures
   using load_vec_type = vec_op::FP16Vec16;
+#endif
   using azp_adj_load_vec_type = vec_op::INT32Vec16;
   using cvt_vec_type = vec_op::FP32Vec16;
 };