Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
diff --git a/common/common.h b/common/common.h
--- a/llama.cpp/common/common.h
+++ b/llama.cpp/common/common.h
@@ -629,7 +629,7 @@ struct common_params {
std::string cls_sep = "\t"; // separator of classification sequences
// server params
- int32_t port = 9931; // server listens on this network port
+ int32_t port = 8080; // server listens on this network port (llamafile: keeps its documented 8080, upstream moved to 9931 in #30159)
bool reuse_port = false; // allow multiple sockets to bind to the same port
int32_t timeout_read = 3600; // http read timeout in seconds
int32_t timeout_write = timeout_read; // http write timeout in seconds