upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

server: in SSE mode, send HTTP headers when slot starts (#23884)

Browse Source 
* server: in SSE mode, send HTTP headers when slot starts

* ref to pr

* stream should be false by default
This commit is contained in:
Xuan-Son Nguyen
2026-05-30 00:06:29 +02:00
committed by GitHub
parent 151f3a98e9
commit 0821c5fcfd
3 changed files with 21 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tools/server/server-task.cpp
View File

@@ -1422,6 +1422,9 @@ void server_task_result_cmpl_partial::update(task_result_state & state) {
json server_task_result_cmpl_partial::to_json() {
GGML_ASSERT(is_updated && "update() must be called before to_json()");
if (is_begin) {
return nullptr; // simply signal to HTTP handler to send the headers and status code
}
switch (res_type) {
case TASK_RESPONSE_TYPE_NONE:
return to_json_non_oaicompat();