Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836)

Co-authored-by: Philipp Moritz <pcmoritz@gmail.com>
Co-authored-by: Amir Balwel <amoooori04@gmail.com>
Co-authored-by: root <kuanfu.liu@akirakan.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: kuanfu <kuanfu.liu@embeddedllm.com>
Co-authored-by: miloice <17350011+kliuae@users.noreply.github.com>

csrc/reduction_utils.cuh

@@ -17,13 +17,15 @@
  */
 #pragma once
 
+#include "cuda_compat.h"
+
 namespace vllm {
 
 template<typename T>
 __inline__ __device__ T warpReduceSum(T val) {
 #pragma unroll
   for (int mask = 16; mask > 0; mask >>= 1)
-    val += __shfl_xor_sync(0xffffffff, val, mask, 32);
+    val += VLLM_SHFL_XOR_SYNC(val, mask);
   return val;
 }