From 30699689581f7349aea8a53b1ffbaa4901e176e0 Mon Sep 17 00:00:00 2001
From: Haiyue Wang <haiyuewa@163.com>
Date: Tue, 18 Nov 2025 09:16:26 +0800
Subject: [PATCH] vocab : call reserve() for building plamo-2-translate suffix

Test 'Q4_K_M' quantization on https://huggingface.co/pfnet/plamo-2-translate

The 'suffix_to_score' size is 193510, it needs 19 memory allocation with final
capacity 262144 to hold the value, if not preserve the memory.

Signed-off-by: Haiyue Wang <haiyuewa@163.com>
---
 src/llama-vocab.cpp | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/llama-vocab.cpp b/src/llama-vocab.cpp
index 29e31cecd1565..a73c4c448ba53 100644
--- a/src/llama-vocab.cpp
+++ b/src/llama-vocab.cpp
@@ -1281,6 +1281,7 @@ struct llm_tokenizer_plamo2 : llm_tokenizer {
 
         // Build suffix list in lexicographical order of reversed strings
         std::vector<std::string> suffixes;
+        suffixes.reserve(suffix_to_score.size() + 1);
         for (const auto & pair : suffix_to_score) {
             suffixes.push_back(pair.first);
         }