Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
Fix server initialization order
Justine Tunneyce2e84864862
diff --git a/llama.cpp/server/public/index.html b/llama.cpp/server/public/index.htmlindex 47cb5f76..367ded37 100644--- a/llama.cpp/server/public/index.html+++ b/llama.cpp/server/public/index.html@@ -1018,7 +1018,7 @@<footer><p><${ModelGenerationInfo} /></p>- <p>Powered by <a href="https://github.com/ggerganov/llama.cpp">llama.cpp</a> and <a href="https://ggml.ai">ggml.ai</a>, and <a href="https://github.com/Mozilla-Ocho/llamafile/">llamafile</a></p>+ <p>Powered by <a href="https://github.com/ggerganov/llama.cpp">llama.cpp</a>, <a href="https://ggml.ai">ggml.ai</a>, and <a href="https://github.com/Mozilla-Ocho/llamafile/">llamafile</a></p></footer></div>`;diff --git a/llama.cpp/server/server.cpp b/llama.cpp/server/server.cppindex 4d3a3e27..63fd24a1 100644--- a/llama.cpp/server/server.cpp+++ b/llama.cpp/server/server.cpp@@ -3100,6 +3100,13 @@ int server_cli(int argc, char **argv)log_data["api_key"] = "api_key: " + std::to_string(sparams.api_keys.size()) + " keys loaded";}+ // launch browser tab+ if (!sparams.nobrowser) {+ char url[128];+ snprintf(url, sizeof(url), "http://%s:%d/", connect_host, sparams.port);+ llamafile_launch_browser(url);+ }+if (!FLAG_unsecure) {if (IsXnu()) {// Cosmopolitan libc explicitly does not support cosmo_dlopen on x64@@ -3170,13 +3177,6 @@ int server_cli(int argc, char **argv)return 0;});- // launch browser tab- if (!sparams.nobrowser) {- char url[128];- snprintf(url, sizeof(url), "http://%s:%d/", connect_host, sparams.port);- llamafile_launch_browser(url);- }-if (sparams.chat_template.empty()) { // custom chat template is not supplied// check if the template comes with the model is supported by usllama.validate_model_chat_template(sparams);