thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

server: fix SSE and OpenAI compatibility for error messages when streaming (#16109)

Browse source 
* server: fix SSE and OpenAI compatibility for error messages when streaming

* server: remove obsolete event parameter and use required data fieldname instead
This commit is contained in:
Benni 2025-09-20 07:56:30 +02:00 • committed by GitHub
parent be79d9fdd9
commit 459c0c2c1a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tools/server/utils.hpp
View file

@ -459,9 +459,9 @@ static std::string tokens_to_output_formatted_string(const llama_context * ctx,
return out;
}
static bool server_sent_event(httplib::DataSink & sink, const char * event, const json & data) {
static bool server_sent_event(httplib::DataSink & sink, const json & data) {
const std::string str =
std::string(event) + ": " +
"data: " +
data.dump(-1, ' ', false, json::error_handler_t::replace) +
"\n\n"; // required by RFC 8895 - A message is terminated by a blank line (two line terminators in a row).