ggml: Disable flash attention for gemma2

Our new engine implementation of gemma2 doesn't support flash
attention, which means that it also doesn't support KV cache
quantization. Currently, it is possible to turn these two on,
which will result in a crash.

fs/ggml/ggml.go

@@ -883,6 +883,10 @@ func (f GGML) SupportsFlashAttention() bool {
 		return false
 	}
 
+	if arch := f.KV().Architecture(); slices.Contains([]string{"gemma2"}, arch) {
+		return false
+	}
+
 	// Check head counts match and are non-zero
 	headCountK := f.KV().EmbeddingHeadCountK()
 	headCountV := f.KV().EmbeddingHeadCountV()