diff --git a/src/halfutils.c b/src/halfutils.c
index 2df4995c0..fe5d56802 100644
--- a/src/halfutils.c
+++ b/src/halfutils.c
@@ -239,6 +239,230 @@ HalfvecL1DistanceF16c(int dim, half * ax, half * bx)
 }
 #endif
 
+#ifdef USE_SVE
+#include <arm_sve.h>
+
+#define SVE_HSUM4(pg, a0, a1, a2, a3) \
+	svaddv_f32((pg), svadd_f32_x((pg), svadd_f32_x((pg), (a0), (a1)), svadd_f32_x((pg), (a2), (a3))))
+
+#define SVE2_MIN_DIM 32
+
+#define SVE2_DIFF_BOT(z, one, a, b) svmlslb_f32(svmlalb_f32((z), (a), (one)), (b), (one))
+#define SVE2_DIFF_TOP(z, one, a, b) svmlslt_f32(svmlalt_f32((z), (a), (one)), (b), (one))
+
+TARGET_SVE2 static float
+HalfvecL2SquaredDistanceSve2(int dim, half * ax, half * bx)
+{
+	const float16_t *a = (const float16_t *) ax;
+	const float16_t *b = (const float16_t *) bx;
+	const svbool_t all16 = svptrue_b16();
+	const svbool_t all32 = svptrue_b32();
+	const svfloat16_t one = svdup_n_f16(1.0);
+	const svfloat32_t z = svdup_n_f32(0.0f);
+	const int	vl = (int) svcnth();
+	int			i = 0;
+	svfloat32_t acc0 = z;
+	svfloat32_t acc1 = z;
+	svfloat32_t acc2 = z;
+	svfloat32_t acc3 = z;
+
+	if (dim < SVE2_MIN_DIM)
+		return HalfvecL2SquaredDistanceDefault(dim, ax, bx);
+
+	for (; i + 2 * vl <= dim; i += 2 * vl)
+	{
+		svfloat16_t a0 = svld1_f16(all16, a + i);
+		svfloat16_t b0 = svld1_f16(all16, b + i);
+		svfloat16_t a1 = svld1_f16(all16, a + i + vl);
+		svfloat16_t b1 = svld1_f16(all16, b + i + vl);
+		svfloat32_t d0 = SVE2_DIFF_BOT(z, one, a0, b0);
+		svfloat32_t d1 = SVE2_DIFF_TOP(z, one, a0, b0);
+		svfloat32_t d2 = SVE2_DIFF_BOT(z, one, a1, b1);
+		svfloat32_t d3 = SVE2_DIFF_TOP(z, one, a1, b1);
+
+		acc0 = svmla_f32_x(all32, acc0, d0, d0);
+		acc1 = svmla_f32_x(all32, acc1, d1, d1);
+		acc2 = svmla_f32_x(all32, acc2, d2, d2);
+		acc3 = svmla_f32_x(all32, acc3, d3, d3);
+	}
+
+	for (; i < dim; i += vl)
+	{
+		svbool_t	pg = svwhilelt_b16_s32(i, dim);
+		svfloat16_t a0 = svld1_f16(pg, a + i);
+		svfloat16_t b0 = svld1_f16(pg, b + i);
+		svfloat32_t d0 = SVE2_DIFF_BOT(z, one, a0, b0);
+		svfloat32_t d1 = SVE2_DIFF_TOP(z, one, a0, b0);
+
+		acc0 = svmla_f32_x(all32, acc0, d0, d0);
+		acc1 = svmla_f32_x(all32, acc1, d1, d1);
+	}
+
+	return SVE_HSUM4(all32, acc0, acc1, acc2, acc3);
+}
+
+TARGET_SVE2 static float
+HalfvecInnerProductSve2(int dim, half * ax, half * bx)
+{
+	const float16_t *a = (const float16_t *) ax;
+	const float16_t *b = (const float16_t *) bx;
+	const svbool_t all16 = svptrue_b16();
+	const svbool_t all32 = svptrue_b32();
+	const int	vl = (int) svcnth();
+	int			i = 0;
+	svfloat32_t z = svdup_n_f32(0.0f);
+	svfloat32_t acc0 = z, acc1 = z, acc2 = z, acc3 = z;
+	svfloat32_t acc4 = z, acc5 = z, acc6 = z, acc7 = z;
+
+	if (dim < SVE2_MIN_DIM)
+		return HalfvecInnerProductDefault(dim, ax, bx);
+
+	for (; i + 4 * vl <= dim; i += 4 * vl)
+	{
+		svfloat16_t a0 = svld1_f16(all16, a + i);
+		svfloat16_t b0 = svld1_f16(all16, b + i);
+		svfloat16_t a1 = svld1_f16(all16, a + i + vl);
+		svfloat16_t b1 = svld1_f16(all16, b + i + vl);
+		svfloat16_t a2 = svld1_f16(all16, a + i + 2 * vl);
+		svfloat16_t b2 = svld1_f16(all16, b + i + 2 * vl);
+		svfloat16_t a3 = svld1_f16(all16, a + i + 3 * vl);
+		svfloat16_t b3 = svld1_f16(all16, b + i + 3 * vl);
+
+		acc0 = svmlalb_f32(acc0, a0, b0);
+		acc1 = svmlalt_f32(acc1, a0, b0);
+		acc2 = svmlalb_f32(acc2, a1, b1);
+		acc3 = svmlalt_f32(acc3, a1, b1);
+		acc4 = svmlalb_f32(acc4, a2, b2);
+		acc5 = svmlalt_f32(acc5, a2, b2);
+		acc6 = svmlalb_f32(acc6, a3, b3);
+		acc7 = svmlalt_f32(acc7, a3, b3);
+	}
+
+	for (; i < dim; i += vl)
+	{
+		svbool_t	pg = svwhilelt_b16_s32(i, dim);
+		svfloat16_t a0 = svld1_f16(pg, a + i);
+		svfloat16_t b0 = svld1_f16(pg, b + i);
+
+		acc0 = svmlalb_f32(acc0, a0, b0);
+		acc1 = svmlalt_f32(acc1, a0, b0);
+	}
+
+	acc0 = svadd_f32_x(all32, acc0, acc4);
+	acc1 = svadd_f32_x(all32, acc1, acc5);
+	acc2 = svadd_f32_x(all32, acc2, acc6);
+	acc3 = svadd_f32_x(all32, acc3, acc7);
+	return SVE_HSUM4(all32, acc0, acc1, acc2, acc3);
+}
+
+TARGET_SVE2 static double
+HalfvecCosineSimilaritySve2(int dim, half * ax, half * bx)
+{
+	const float16_t *a = (const float16_t *) ax;
+	const float16_t *b = (const float16_t *) bx;
+	const svbool_t all16 = svptrue_b16();
+	const svbool_t all32 = svptrue_b32();
+	const int	vl = (int) svcnth();
+	int			i = 0;
+	svfloat32_t zero = svdup_n_f32(0.0f);
+	svfloat32_t s0 = zero, s1 = zero, s2 = zero, s3 = zero;
+	svfloat32_t na0 = zero, na1 = zero, na2 = zero, na3 = zero;
+	svfloat32_t nb0 = zero, nb1 = zero, nb2 = zero, nb3 = zero;
+	float		similarity;
+	float		norma;
+	float		normb;
+
+	if (dim < SVE2_MIN_DIM)
+		return HalfvecCosineSimilarityDefault(dim, ax, bx);
+
+	for (; i + 2 * vl <= dim; i += 2 * vl)
+	{
+		svfloat16_t a0 = svld1_f16(all16, a + i);
+		svfloat16_t b0 = svld1_f16(all16, b + i);
+		svfloat16_t a1 = svld1_f16(all16, a + i + vl);
+		svfloat16_t b1 = svld1_f16(all16, b + i + vl);
+
+		s0 = svmlalb_f32(s0, a0, b0);
+		s1 = svmlalt_f32(s1, a0, b0);
+		s2 = svmlalb_f32(s2, a1, b1);
+		s3 = svmlalt_f32(s3, a1, b1);
+		na0 = svmlalb_f32(na0, a0, a0);
+		na1 = svmlalt_f32(na1, a0, a0);
+		na2 = svmlalb_f32(na2, a1, a1);
+		na3 = svmlalt_f32(na3, a1, a1);
+		nb0 = svmlalb_f32(nb0, b0, b0);
+		nb1 = svmlalt_f32(nb1, b0, b0);
+		nb2 = svmlalb_f32(nb2, b1, b1);
+		nb3 = svmlalt_f32(nb3, b1, b1);
+	}
+
+	for (; i < dim; i += vl)
+	{
+		svbool_t	pg = svwhilelt_b16_s32(i, dim);
+		svfloat16_t a0 = svld1_f16(pg, a + i);
+		svfloat16_t b0 = svld1_f16(pg, b + i);
+
+		s0 = svmlalb_f32(s0, a0, b0);
+		s1 = svmlalt_f32(s1, a0, b0);
+		na0 = svmlalb_f32(na0, a0, a0);
+		na1 = svmlalt_f32(na1, a0, a0);
+		nb0 = svmlalb_f32(nb0, b0, b0);
+		nb1 = svmlalt_f32(nb1, b0, b0);
+	}
+
+	similarity = SVE_HSUM4(all32, s0, s1, s2, s3);
+	norma = SVE_HSUM4(all32, na0, na1, na2, na3);
+	normb = SVE_HSUM4(all32, nb0, nb1, nb2, nb3);
+
+	return (double) similarity / sqrt((double) norma * (double) normb);
+}
+
+TARGET_SVE2 static float
+HalfvecL1DistanceSve2(int dim, half * ax, half * bx)
+{
+	const float16_t *a = (const float16_t *) ax;
+	const float16_t *b = (const float16_t *) bx;
+	const svbool_t all16 = svptrue_b16();
+	const svbool_t all32 = svptrue_b32();
+	const svfloat16_t one = svdup_n_f16(1.0);
+	const svfloat32_t z = svdup_n_f32(0.0f);
+	const int	vl = (int) svcnth();
+	int			i = 0;
+	svfloat32_t acc0 = z;
+	svfloat32_t acc1 = z;
+	svfloat32_t acc2 = z;
+	svfloat32_t acc3 = z;
+
+	if (dim < SVE2_MIN_DIM)
+		return HalfvecL1DistanceDefault(dim, ax, bx);
+
+	for (; i + 2 * vl <= dim; i += 2 * vl)
+	{
+		svfloat16_t a0 = svld1_f16(all16, a + i);
+		svfloat16_t b0 = svld1_f16(all16, b + i);
+		svfloat16_t a1 = svld1_f16(all16, a + i + vl);
+		svfloat16_t b1 = svld1_f16(all16, b + i + vl);
+
+		acc0 = svadd_f32_x(all32, acc0, svabs_f32_x(all32, SVE2_DIFF_BOT(z, one, a0, b0)));
+		acc1 = svadd_f32_x(all32, acc1, svabs_f32_x(all32, SVE2_DIFF_TOP(z, one, a0, b0)));
+		acc2 = svadd_f32_x(all32, acc2, svabs_f32_x(all32, SVE2_DIFF_BOT(z, one, a1, b1)));
+		acc3 = svadd_f32_x(all32, acc3, svabs_f32_x(all32, SVE2_DIFF_TOP(z, one, a1, b1)));
+	}
+
+	for (; i < dim; i += vl)
+	{
+		svbool_t	pg = svwhilelt_b16_s32(i, dim);
+		svfloat16_t a0 = svld1_f16(pg, a + i);
+		svfloat16_t b0 = svld1_f16(pg, b + i);
+
+		acc0 = svadd_f32_x(all32, acc0, svabs_f32_x(all32, SVE2_DIFF_BOT(z, one, a0, b0)));
+		acc1 = svadd_f32_x(all32, acc1, svabs_f32_x(all32, SVE2_DIFF_TOP(z, one, a0, b0)));
+	}
+
+	return SVE_HSUM4(all32, acc0, acc1, acc2, acc3);
+}
+#endif							/* USE_SVE */
+
 #ifdef HALFVEC_DISPATCH
 #define CPU_FEATURE_FMA     (1 << 12)
 #define CPU_FEATURE_OSXSAVE (1 << 27)
@@ -297,4 +521,14 @@ HalfvecInit(void)
 		HalfvecL1Distance = HalfvecL1DistanceF16c;
 	}
 #endif
-}
+
+#ifdef USE_SVE
+	if (SVE2_RUNTIME_SUPPORTED())
+	{
+		HalfvecL2SquaredDistance = HalfvecL2SquaredDistanceSve2;
+		HalfvecInnerProduct = HalfvecInnerProductSve2;
+		HalfvecCosineSimilarity = HalfvecCosineSimilaritySve2;
+		HalfvecL1Distance = HalfvecL1DistanceSve2;
+	}
+#endif
+}
\ No newline at end of file
diff --git a/src/halfvec.h b/src/halfvec.h
index 8ff2cbfbf..cd00e02e7 100644
--- a/src/halfvec.h
+++ b/src/halfvec.h
@@ -38,6 +38,42 @@
 #define USE__GET_CPUID
 #endif
 
+#ifndef DISABLE_DISPATCH
+#if defined(__aarch64__) && defined(__linux__) && defined(__has_include)
+#if __has_include(<arm_sve.h>) && __has_include(<sys/auxv.h>)
+#if (defined(__clang__) && __clang_major__ >= 16) || \
+	(!defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 12)
+#define USE_SVE
+#endif
+#endif
+#endif
+#endif
+
+#ifdef USE_SVE
+#include <sys/auxv.h>
+
+#ifndef AT_HWCAP2
+#define AT_HWCAP2 26
+#endif
+#ifndef HWCAP_SVE
+#define HWCAP_SVE (1 << 22)
+#endif
+#ifndef HWCAP2_SVE2
+#define HWCAP2_SVE2 (1 << 1)
+#endif
+
+#if defined(__clang__)
+#define TARGET_SVE __attribute__((target("sve")))
+#define TARGET_SVE2 __attribute__((target("sve2")))
+#else
+#define TARGET_SVE __attribute__((target("+sve")))
+#define TARGET_SVE2 __attribute__((target("+sve2")))
+#endif
+
+#define SVE_RUNTIME_SUPPORTED()  ((getauxval(AT_HWCAP) & HWCAP_SVE) != 0)
+#define SVE2_RUNTIME_SUPPORTED() ((getauxval(AT_HWCAP2) & HWCAP2_SVE2) != 0)
+#endif
+
 #if defined(USE_DISPATCH)
 #define HALFVEC_DISPATCH
 #endif
