From 0b3e42a5f80b7221c21ac63444141890a8f4a8dc Mon Sep 17 00:00:00 2001
From: reversebias <cam@reversebias.net>
Date: Sat, 9 Mar 2024 23:00:12 +1100
Subject: [PATCH] Explicitly enable prompt caching on llama.cpp endpoints

---
 src/lib/server/endpoints/llamacpp/endpointLlamacpp.ts | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/lib/server/endpoints/llamacpp/endpointLlamacpp.ts b/src/lib/server/endpoints/llamacpp/endpointLlamacpp.ts
index faa08c8f55b..2ace6f403f2 100644
--- a/src/lib/server/endpoints/llamacpp/endpointLlamacpp.ts
+++ b/src/lib/server/endpoints/llamacpp/endpointLlamacpp.ts
@@ -41,6 +41,7 @@ export function endpointLlamacpp(
 				stop: model.parameters.stop,
 				repeat_penalty: model.parameters.repetition_penalty,
 				n_predict: model.parameters.max_new_tokens,
+				cache_prompt: true,
 			}),
 		});