tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-12 11:27:43 -04:00
Code Issues Packages Projects Releases Wiki Activity

server : fix cache_tokens bug with no cache_prompt (#13533)

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2025-05-14 13:35:07 +02:00
committed by GitHub
parent 09d13d94fb
commit 360a9c98e1
3 changed files with 25 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/utils.hpp
View File

@@ -1153,7 +1153,7 @@ public:
tokens.clear();
}
void resize(size_t n) {
void keep_first(size_t n) {
GGML_ASSERT(n <= tokens.size());
if (has_mtmd) {
// we throw an error if we try to remove a token in the middle of an image