Update src/Microsoft.ML.Tokenizers/Utils/BytePairEncoder.cs

stephentoub · Copilot · web-flow · commit 394658eedd10 · 2026-02-12T21:21:28.000-05:00
Co-authored-by: Copilot &lt;175728472+Copilot@users.noreply.github.com&gt;
diff --git a/src/Microsoft.ML.Tokenizers/Utils/BytePairEncoder.cs b/src/Microsoft.ML.Tokenizers/Utils/BytePairEncoder.cs
@@ -170,7 +170,7 @@ private static (int Id, int TokenIndex, int TokenLength)[] BytePairEncodeLarge(R
                 CurRank = int.MaxValue
             };
 
-            var heap = new PriorityQueue<MergeEntry>();
+            var heap = new PriorityQueue<MergeEntry>(0);
 
             for (int i = 0; i < mergingBytes.Length - 1; i++)
             {

Original file line number	Diff line number	Diff line change
`@@ -170,7 +170,7 @@ private static (int Id, int TokenIndex, int TokenLength)[] BytePairEncodeLarge(R`
`170`	`170`	`CurRank = int.MaxValue`
`171`	`171`	`};`
`172`	`172`
`173`		`- var heap = new PriorityQueue<MergeEntry>();`
	`173`	`+ var heap = new PriorityQueue<MergeEntry>(0);`
`174`	`174`
`175`	`175`	`for (int i = 0; i < mergingBytes.Length - 1; i++)`
`176`	`176`	`{`