From 5fa709a3f4cd93cbec176b78fc2a3abf609dd757 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Fri, 6 Mar 2026 18:37:40 -0800 Subject: [PATCH] llama.cpp server: use port+5 offset and suppress No parser definition detected logs --- modules/llama_cpp_server.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/modules/llama_cpp_server.py b/modules/llama_cpp_server.py index 32494978..12ff173e 100644 --- a/modules/llama_cpp_server.py +++ b/modules/llama_cpp_server.py @@ -320,8 +320,8 @@ class LlamaServer: return False def _find_available_port(self): - """Find an available port, preferring main port + 1.""" - preferred_port = shared.args.api_port + 1 + """Find an available port, preferring main port + 5.""" + preferred_port = shared.args.api_port + 5 if self._is_port_available(preferred_port): return preferred_port @@ -510,6 +510,7 @@ class LlamaServer: self.process.wait(timeout=5) except subprocess.TimeoutExpired: self.process.kill() + self.process.wait(timeout=5) self.process = None @@ -560,7 +561,7 @@ def filter_stderr_with_progress(process_stderr): last_was_progress = (progress < 1.0) # skip noise lines - elif not (line.startswith(('srv ', 'slot ')) or 'log_server_r: request: GET /health' in line): + elif not (line.startswith(('srv ', 'slot ')) or 'log_server_r: request: GET /health' in line or 'No parser definition detected' in line): # if we were in progress, finish that line first if last_was_progress: print(file=sys.stderr)