diff --git a/onnxruntime/core/mlas/lib/amd64/cvtfp16Avx.asm b/onnxruntime/core/mlas/lib/amd64/cvtfp16Avx.asm
index c7f6342c527bf..800863c77a230 100644
--- a/onnxruntime/core/mlas/lib/amd64/cvtfp16Avx.asm
+++ b/onnxruntime/core/mlas/lib/amd64/cvtfp16Avx.asm
@@ -54,7 +54,7 @@ HIGH_SELECTOR   equ 00110001b
 
 LEAF_ENTRY MlasCastF16ToF32KernelAvx, _TEXT
 
-	test    r8, r8                  ; Check if we have any elements to convert
+    test    r8, r8                  ; Check if we have any elements to convert
     jz      ExitRoutine
     cmp     r8, 8
     jb      ConvertMaskedVectors
@@ -80,6 +80,8 @@ Convert256Vectors:
         jz      ExitRoutine ; If we are done, exit
         cmp     r8, 16      ; If the vector is big enough, we go again
         jae     Convert256Vectors
+        cmp     r8, 8       ; Check if we have enough elements to convert
+        jb      ConvertMaskedVectors
 
 
 
diff --git a/onnxruntime/core/mlas/lib/x86_64/cvtfp16Avx.S b/onnxruntime/core/mlas/lib/x86_64/cvtfp16Avx.S
index 1a70061460e50..a4d730fa513ab 100644
--- a/onnxruntime/core/mlas/lib/x86_64/cvtfp16Avx.S
+++ b/onnxruntime/core/mlas/lib/x86_64/cvtfp16Avx.S
@@ -51,8 +51,6 @@ FUNCTION_ENTRY MlasCastF16ToF32KernelAvx
 
         test    rdx, rdx      // Check if we have any elements to convert
         jz      ExitRoutine
-
-AVX_NE_CONVERT:
         cmp     rdx, 8
         jb      ConvertMaskedVectors
         cmp     rdx, 16
@@ -75,6 +73,8 @@ Convert256Vectors:
         jz      ExitRoutine     // If we are done, exit
         cmp     rdx, 16         // If the vector is big enough, we go again
         jae     Convert256Vectors
+        cmp	rdx, 8           // Check if we have enough elements to convert
+        jb      ConvertMaskedVectors