From 06506529eab28cc3cb4767464f18d7b92a557bf9 Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot
 <306269227+localai-org-maint-bot@users.noreply.github.com>
Date: Fri, 31 Jul 2026 03:06:34 +0000
Subject: [PATCH] fix(cachyllama): link SSD cache implementation

CachyLLaMA splits persistent prompt-cache support into separate source files. Include those implementations in the monolithic LocalAI gRPC adapter when the fork provides them so the ARM64 fallback build resolves the page-manager symbols.

Assisted-by: Codex:gpt-5 [Codex]
---
 backend/cpp/llama-cpp/grpc-server.cpp | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/backend/cpp/llama-cpp/grpc-server.cpp b/backend/cpp/llama-cpp/grpc-server.cpp
index 67d5ef11f..c715eaad6 100644
--- a/backend/cpp/llama-cpp/grpc-server.cpp
+++ b/backend/cpp/llama-cpp/grpc-server.cpp
@@ -43,6 +43,15 @@
 #if __has_include("server-stream.cpp")
 #include "server-stream.cpp"
 #endif
+// CachyLLaMA splits its persistent prompt-cache implementation out of
+// server-context.cpp. Pull both implementation files into this monolithic
+// adapter TU when present; older llama.cpp pins do not ship them.
+#if __has_include("server-context-ssd-cache.cpp")
+#include "server-context-ssd-cache.cpp"
+#endif
+#if __has_include("server-context-page-manager.cpp")
+#include "server-context-page-manager.cpp"
+#endif
 #include "server-context.cpp"
 
 // LocalAI