8000 server : allow requests larger than 8K (#4500) · Pints-AI/llama.cpp@62bd52b · GitHub
[go: up one dir, main page]

Skip to content

Commit 62bd52b

Browse files
authored
server : allow requests larger than 8K (ggml-org#4500)
1 parent 5daa5f5 commit 62bd52b

File tree

1 file changed

+2
-1
lines changed

1 file changed

+2
-1
lines changed

examples/server/server.cpp

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,8 @@
1010
// crash the server in debug mode, otherwise send an http 500 error
1111
#define CPPHTTPLIB_NO_EXCEPTIONS 1
1212
#endif
13-
13+
// increase max payload length to allow use of larger context size
14+
#define CPPHTTPLIB_FORM_URL_ENCODED_PAYLOAD_MAX_LENGTH 1048576
1415
#include "httplib.h"
1516
#include "json.hpp"
1617

0 commit comments

Comments
 (0)
0