3 files changed, 11 insertions, 2 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/gemm_qint8.cpp b/src/core/NEON/kernels/arm_gemm/gemm_qint8.cpp
index 7c860a24a1..d1c4e49edb 100644
--- a/src/core/NEON/kernels/arm_gemm/gemm_qint8.cpp
+++ b/src/core/NEON/kernels/arm_gemm/gemm_qint8.cpp
@@ -71,7 +71,7 @@ static const GemmImplementation<int8_t, int8_t, Requantize32> gemm_qint8_methods
 #ifdef ARM_COMPUTE_ENABLE_SVE
 #ifdef ARM_COMPUTE_ENABLE_SME2
 {
-    GemmMethod::GEMM_HYBRID,
+    GemmMethod::GEMV_PRETRANSPOSED,
     "sme2_gemv_s8qa_dot_16VL",
     [](const GemmArgs &args, const Requantize32 &qp) { return args._ci->has_sme2() && quant_hybrid_asymmetric(qp) && args._Msize == 1 && !args._indirect_input && args._nbatches == 1;  },
     nullptr,
diff --git a/src/core/NEON/kernels/arm_gemm/gemm_quint8.cpp b/src/core/NEON/kernels/arm_gemm/gemm_quint8.cpp
index 3baf9857da..b85b1c4fcf 100644
--- a/src/core/NEON/kernels/arm_gemm/gemm_quint8.cpp
+++ b/src/core/NEON/kernels/arm_gemm/gemm_quint8.cpp
@@ -67,7 +67,7 @@ static const GemmImplementation<uint8_t, uint8_t, Requantize32> gemm_quint8_meth
 #ifdef ARM_COMPUTE_ENABLE_SME2
 // SME kernels
 {
-    GemmMethod::GEMM_HYBRID,
+    GemmMethod::GEMV_PRETRANSPOSED,
     "sme2_gemv_u8qa_dot_16VL",
     [](const GemmArgs &args, const Requantize32 &qp) { return args._ci->has_sme2() && quant_hybrid_asymmetric(qp) && args._Msize == 1 && !args._indirect_input && args._nbatches == 1;  },
     nullptr,
diff --git a/src/core/NEON/kernels/arm_gemm/gemv_pretransposed.hpp b/src/core/NEON/kernels/arm_gemm/gemv_pretransposed.hpp
index f70fc98572..92c884ce18 100644
--- a/src/core/NEON/kernels/arm_gemm/gemv_pretransposed.hpp
+++ b/src/core/NEON/kernels/arm_gemm/gemv_pretransposed.hpp
@@ -215,6 +215,15 @@ public:
         }
     }
 
+    void set_quantized_bias(const int32_t *bias, size_t bias_multi_stride) override {
+        if (std::is_same<OutputStage, Requantize32>::value) {
+            Requantize32 *qp = reinterpret_cast<Requantize32 *>(&_os);
+
+            qp->bias = bias;
+            qp->bias_multi_stride = bias_multi_stride;
+        }
+    }
+
     void pretranspose_B_array(void *buffer, const To *B, const int ldb, const int B_multi_stride, bool transposed) override {
         assert(!transposed);