Skip to content

Distribute and run LLMs with a single file.

Avoid bind() conflicts on port 8080 w/ server

Justine Tunneyc1c8683d3782
diff --git a/llama.cpp/README.llamafile b/llama.cpp/README.llamafile
index 4efc2136..e5ee79f5 100644
--- a/llama.cpp/README.llamafile
+++ b/llama.cpp/README.llamafile
@@ -33,6 +33,7 @@ LOCAL MODIFICATIONS
- Introduce pledge() SECCOMP sandboxing to improve security
- Introduce ggml_interrupt() to gracefully handle signals
- Remove log callback pointer API from Metal GPU module
+ - Avoid bind() conflicts on port 8080 w/ server
- Allow --grammar to be used on --image prompts
- Use runtime dispatching for matmul quants
- Remove operating system #ifdef statements
diff --git a/llama.cpp/server/server.cpp b/llama.cpp/server/server.cpp
index 172e4a26..1a3d66ec 100644
--- a/llama.cpp/server/server.cpp
+++ b/llama.cpp/server/server.cpp
@@ -2994,10 +2994,15 @@ int main(int argc, char **argv)
svr.set_read_timeout (sparams.read_timeout);
svr.set_write_timeout(sparams.write_timeout);
- if (!svr.bind_to_port(sparams.hostname, sparams.port))
- {
- fprintf(stderr, "\ncouldn't bind to server socket: hostname=%s port=%d\n\n", sparams.hostname.c_str(), sparams.port);
- return 1;
+ for (int i = 0;; ++i) {
+ if (svr.bind_to_port(sparams.hostname, sparams.port)) {
+ break;
+ } else if (i < 10) {
+ ++sparams.port;
+ } else {
+ fprintf(stderr, "\ncouldn't bind to server socket: hostname=%s port=%d\n\n", sparams.hostname.c_str(), sparams.port);
+ return 1;
+ }
}
// Set the base directory for serving static files