build(llama-cpp): isolate paged patches in patches/paged/ behind LLAMA_PAGED flag (default on)

Move the paged-attention patch series (0001-0004 + docs) into patches/paged/,
applied behind a new LLAMA_PAGED build flag (default on). The base patches/ dir is
now clean, so a dep-bump that breaks a paged hook can be unblocked with
LLAMA_PAGED=off (clean-against-upstream build) and the paged carry fixed
independently - decoupling the paged-KV maintenance from routine bumps without a
separate backend. Both apply paths wired (Makefile git-apply + prepare.sh re-apply,
flag passed through). Runtime stays gated by LLAMA_KV_PAGED env, so an on build is
byte-identical to stock until that env is set. Glob/flag logic verified in bash.

Assisted-by: Claude:opus-4.8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

backend/cpp/llama-cpp/Makefile

@@ -1,6 +1,14 @@
 
 LLAMA_VERSION?=f3e182816421c648188b5eab269853bf1531d950
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
+# LLAMA_PAGED controls whether the vendored paged-attention patch series
+# (patches/paged/) is applied on top of the pinned llama.cpp. Default on; set
+# LLAMA_PAGED=off to build a clean-against-upstream backend (e.g. to unblock a
+# dep-bump if an upstream change breaks a paged hook - the paged carry is then
+# fixed independently). Runtime behaviour stays gated by the LLAMA_KV_PAGED env
+# regardless, so an LLAMA_PAGED=on build is byte-identical to stock until that
+# env is set.
+LLAMA_PAGED?=on
 
 CMAKE_ARGS?=
 BUILD_TYPE?=
@@ -142,14 +150,23 @@ llama.cpp:
 		[ -e "$$p" ] || continue; \
 		echo "applying llama.cpp patch: $$p"; \
 		git apply --verbose "$$p" || { echo "patch failed: $$p"; exit 1; }; \
-	done
+	done && \
+	if [ "$(LLAMA_PAGED)" = "off" ]; then \
+		echo "LLAMA_PAGED=off: skipping paged-attention patch series"; \
+	else \
+		for p in $(CURRENT_MAKEFILE_DIR)patches/paged/0*.patch; do \
+			[ -e "$$p" ] || continue; \
+			echo "applying llama.cpp PAGED patch: $$p"; \
+			git apply --verbose "$$p" || { echo "paged patch failed: $$p"; exit 1; }; \
+		done; \
+	fi
 
 llama.cpp/tools/grpc-server: llama.cpp
 	mkdir -p llama.cpp/tools/grpc-server
-	bash prepare.sh
+	LLAMA_PAGED=$(LLAMA_PAGED) bash prepare.sh
 
 rebuild:
-	bash prepare.sh
+	LLAMA_PAGED=$(LLAMA_PAGED) bash prepare.sh
 	rm -rf grpc-server
 	$(MAKE) grpc-server
 

backend/cpp/llama-cpp/prepare.sh

@@ -2,12 +2,23 @@
 
 ## Patches
 
-## Apply patches from the `patches` directory
+## Apply patches: the base `patches/` series, then the gated `patches/paged/`
+## series (default on; LLAMA_PAGED=off skips it). Runs before `set -e` so a
+## re-apply on rebuild is tolerated. Only *.patch files are applied (docs/dirs
+## like patches/paged/ and *.md are skipped).
 if [ -d "patches" ]; then
-    for patch in $(ls patches); do
+    for patch in patches/*.patch; do
+        [ -e "$patch" ] || continue
         echo "Applying patch $patch"
-        patch -d llama.cpp/ -p1 < patches/$patch
-    done 
+        patch -d llama.cpp/ -p1 < "$patch"
+    done
+    if [ "${LLAMA_PAGED:-on}" != "off" ] && [ -d "patches/paged" ]; then
+        for patch in patches/paged/*.patch; do
+            [ -e "$patch" ] || continue
+            echo "Applying paged patch $patch"
+            patch -d llama.cpp/ -p1 < "$patch"
+        done
+    fi
 fi
 
 set -e