From 770462aace37d543b9c5c970c8c3888f5987c48e Mon Sep 17 00:00:00 2001
From: Xuan Son Nguyen <son@huggingface.co>
Date: Mon, 23 Sep 2024 15:20:29 +0200
Subject: [PATCH] revert usage of GGML_ASSERT

---
 examples/server/server.cpp | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 3693cf747..8655c097a 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -1837,8 +1837,10 @@ struct server_context {
             if (slot.ga_n == 1) {
                 if (slot.is_processing() && (int) system_tokens.size() + slot.n_past >= slot.n_ctx - 1) {
                     if (!params.ctx_shift) {
+                        // this check is redundant (for good)
                         // we should never get here, because generation should already stopped in process_token()
-                        GGML_ASSERT(false && "context shifting is disabled");
+                        slot.release();
+                        send_error(slot, "context shift is disabled", ERROR_TYPE_SERVER);
                         continue;
                     }