Fix false positive CPU backend error in test configuration

The test configuration was treating 'CPU backend' as a failure pattern,
but this is incorrect. Loading the CPU backend library is normal - ollama
loads both CUDA and CPU backends for fallback operations.

The log line 'load_backend: loaded CPU backend from libggml-cpu-*.so'
is a success message, not an error.

Changed failure patterns from:
- 'CPU backend' (too broad, matches normal loading)
- 'failed to load.*CUDA' (too specific)

To more accurate patterns:
- 'failed to load.*backend' (matches actual load failures)
- 'backend.*failed' (matches failure messages)

This prevents false positives while still catching real backend failures.

test/config/models.yaml

@@ -54,8 +54,8 @@ profiles:
           - "CUDA.*error"
           - "out of memory"
           - "OOM"
-          - "CPU backend"
-          - "failed to load"
+          - "failed to load.*backend"
+          - "backend.*failed"
 
 # Validation rules applied to all tests (unless overridden in profile)
 validation:
@@ -75,8 +75,8 @@ validation:
       - "CUDA.*error"
       - "out of memory"
       - "OOM"
-      - "CPU backend"
-      - "failed to load"
+      - "failed to load.*backend"
+      - "backend.*failed"
     warning:
       - "fallback"
       - "using CPU"

test/config/quick.yaml

@@ -22,7 +22,8 @@ validation:
     failure:
       - "CUDA.*error"
       - "out of memory"
-      - "failed to load.*CUDA"
+      - "failed to load.*backend"
+      - "backend.*failed"
       - "no GPU detected"
 
 server: