diff --git a/tools/server/server.cpp b/tools/server/server.cpp
index 8538427f73..81e75a307f 100644
--- a/tools/server/server.cpp
+++ b/tools/server/server.cpp
@@ -73,17 +73,23 @@ int main(int argc, char ** argv, char ** envp) {
         return 1;
     }
 
-    // validate batch size for embeddings
-    // embeddings require all tokens to be processed in a single ubatch
-    // see https://github.com/ggml-org/llama.cpp/issues/12836
-    if (params.embedding && params.n_batch > params.n_ubatch) {
-        LOG_WRN("%s: embeddings enabled with n_batch (%d) > n_ubatch (%d)\n", __func__, params.n_batch, params.n_ubatch);
-        LOG_WRN("%s: setting n_batch = n_ubatch = %d to avoid assertion failure\n", __func__, params.n_ubatch);
-        params.n_batch = params.n_ubatch;
+    // validate batch size for embeddings and reranking
+    // non-causal attention (embeddings/reranking) requires n_batch == n_ubatch
+    // see https://github.com/ggml-org/llama.cpp/issues/6263
+    if (params.embedding && params.n_batch != params.n_ubatch) {
+        LOG_WRN("%s: embeddings/reranking mode requires n_batch == n_ubatch\n", __func__);
+        LOG_WRN("%s: setting both to min(%d, %d) = %d to avoid configuration issues\n",
+                __func__, params.n_batch, params.n_ubatch,
+                std::min(params.n_batch, params.n_ubatch));
+        params.n_batch = params.n_ubatch = std::min(params.n_batch, params.n_ubatch);
     }
 
-    if (params.n_parallel < 0) {
-        LOG_INF("%s: n_parallel is set to auto, using n_parallel = 4 and kv_unified = true\n", __func__);
+    // TODO: should we have a separate n_parallel parameter for the server?
+    //       https://github.com/ggml-org/llama.cpp/pull/16736#discussion_r2483763177
+    // TODO: this is a common configuration that is suitable for most local use cases
+    //       however, overriding the parameters is a bit confusing - figure out something more intuitive
+    if (params.n_parallel == 1 && params.kv_unified == false && !params.has_speculative()) {
+        LOG_WRN("%s: setting n_parallel = 4 and kv_unified = true (add -kvu to disable this)\n", __func__);
 
         params.n_parallel = 4;
         params.kv_unified = true;