context : fix SWA-related warning for multiple sequences (#14045)

diff --git a/src/llama-context.cpp b/src/llama-context.cpp
index d94bf8643492197db9e34ce963825338090260e6..ea191068554f021c02729dcb3dc0620aae85e0a9 100644 (file)
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@@ -123,7 +123,7 @@ llama_context::llama_context(
                 __func__, n_ctx_per_seq, hparams.n_ctx_train);
     }
 
-    if (!params.swa_full && cparams.n_seq_max > 1) {
+    if (!params.swa_full && cparams.n_seq_max > 1 && hparams.is_swa_any()) {
         LLAMA_LOG_WARN("%s: requested n_seq_max (%u) > 1, but swa_full is not enabled -- performance may be degraded: %s\n",
                 __func__, cparams.n_seq_max, "https://github.com/ggml-org/llama.cpp/pull/13845#issuecomment-2924800573");
     }