Skip to content

LLM inference in C/C++

C++ ggml

server : do not parse when flushing http headers (#24281)

Aldehir Rojas42a0afd59431
diff --git a/tools/server/server-task.cpp b/tools/server/server-task.cpp
index 842be2ad3d..72a4bd076a 100644
--- a/tools/server/server-task.cpp
+++ b/tools/server/server-task.cpp
@@ -1393,6 +1393,9 @@ json server_task_result_cmpl_final::to_json_anthropic_stream() {
//
void server_task_result_cmpl_partial::update(task_result_state & state) {
is_updated = true;
+ if (is_begin) {
+ return; // begin marker only flushes headers, skip parsing
+ }
state.update_chat_msg(content, true, oaicompat_msg_diffs);
// Copy current state for use in to_json_*() (reflects state BEFORE this chunk)