From: Haiyue Wang <redacted>
Date: Tue, 18 Nov 2025 17:58:22 +0000 (+0800)
Subject: vocab : call reserve() for building plamo-2-translate suffix (#17343)
X-Git-Tag: upstream/0.0.7446~348
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=a045492088dd105231cc5f8bfaae2d527ce47344;p=pkg%2Fggml%2Fsources%2Fllama.cpp

vocab : call reserve() for building plamo-2-translate suffix (#17343)

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 <redacted>
---

diff --git a/src/llama-vocab.cpp b/src/llama-vocab.cpp
index 29e31cec..a73c4c44 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);
         }