happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

server : fix processing of multiple back-to-back mtmd chunks (#21107)

This commit is contained in:
Georgi Gerganov 2026-03-28 16:27:36 +02:00 committed by GitHub
parent 3d66da1809
commit edfb440a2f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/server-context.cpp
View File

@ -2493,7 +2493,7 @@ private:
bool has_mtmd = false;
// check if we should process the image
if (slot.prompt.n_tokens() < slot.task->n_tokens() && input_tokens[slot.prompt.n_tokens()] == LLAMA_TOKEN_NULL) {
while (slot.prompt.n_tokens() < slot.task->n_tokens() && input_tokens[slot.prompt.n_tokens()] == LLAMA_TOKEN_NULL) {
// process the image
size_t n_tokens_out = 0;
int32_t res = input_tokens.process_chunk(ctx, mctx, slot.prompt.n_tokens(), slot.prompt.tokens.pos_next(), slot.id, n_tokens_out);