[Hardware][CPU] Vllm int8 quantization enablement for ARM CPU (#14129)

Signed-off-by: nishith-fujitsu <nishith.jaiswal@fujitsu.com>
2025-07-10 21:29:04 +05:30
parent 4b9a9435bb
commit c7753a9809
5 changed files with 347 additions and 30 deletions
--- a/csrc/cpu/torch_bindings.cpp
+++ b/csrc/cpu/torch_bindings.cpp
@@ -151,8 +151,9 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
  ops.impl("rotary_embedding", torch::kCPU, &rotary_embedding);

  // Quantization
-#ifdef __AVX512F__
+#if defined(__AVX512F__) || defined(__aarch64__)
  at::Tag stride_tag = at::Tag::needs_fixed_stride_order;
+
  // Compute int8 quantized tensor for given scaling factor.
  ops.def(
      "static_scaled_int8_quant(Tensor! out, Tensor input, Tensor scale,"