From f1d4c7f96946953bda8918170899a5bac8fb99ca Mon Sep 17 00:00:00 2001 From: Shang Chieh Tseng Date: Thu, 30 Oct 2025 15:39:17 +0800 Subject: [PATCH] Fix test config: don't treat CPU backend loading as failure The failure pattern 'CPU backend' was incorrectly flagging the normal log message 'load_backend: loaded CPU backend from...' as an error. This is expected behavior - both CUDA and CPU backends are loaded, but GPU is actually used for computation (as shown by 'offloaded 35/35 layers to GPU'). Changed failure patterns to detect actual GPU failures: - Removed: 'CPU backend' (too broad, catches normal backend loading) - Added: 'failed to load.*CUDA' (actual load failures) - Added: 'no GPU detected' (GPU not available) Root cause: monitor.go processes failure patterns first (highest priority), so the 'CPU backend' pattern was creating EventError events before success patterns could be checked, causing tests to fail despite GPU working. --- test/config/quick.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/test/config/quick.yaml b/test/config/quick.yaml index 317f3ce4..985e6c3e 100644 --- a/test/config/quick.yaml +++ b/test/config/quick.yaml @@ -22,7 +22,8 @@ validation: failure: - "CUDA.*error" - "out of memory" - - "CPU backend" + - "failed to load.*CUDA" + - "no GPU detected" server: host: "localhost"