Merge branch 'master' into feat/dllm-backend

Author: localai-org-maint-bot

.docker/llama-cpp-compile.sh

@@ -28,6 +28,10 @@ if [ -z "${BUILD_TYPE:-}" ]; then
   # variants with it (the host never *selects* SME unless it has it, but every variant must
   # still compile).
   if [ "${TARGETARCH}" = "arm64" ]; then
+    # The prebuilt base inherits default ports.ubuntu.com sources; honor the
+    # APT_*_MIRROR build args here like the from-source path does, so this
+    # apt step survives a mirror outage.
+    sh /LocalAI/.docker/apt-mirror.sh || true
     apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
     export CC=gcc-14 CXX=g++-14
   fi

backend/Dockerfile.llama-cpp

@@ -111,6 +111,10 @@ RUN make -BC /LocalAI/backend/cpp/llama-cpp package
 # ============================================================================
 FROM ${BUILDER_BASE_IMAGE} AS builder-prebuilt
 
+ARG APT_MIRROR
+ENV APT_MIRROR=${APT_MIRROR}
+ARG APT_PORTS_MIRROR
+ENV APT_PORTS_MIRROR=${APT_PORTS_MIRROR}
 ARG BUILD_TYPE
 ENV BUILD_TYPE=${BUILD_TYPE}
 ARG CUDA_DOCKER_ARCH

backend/backend.proto

@@ -181,6 +181,13 @@ message ScoreRequest {
   // PredictOptions.ModelIdentity for the full rationale. Empty means "no
   // identity supplied" and backends MUST skip the check.
   string ModelIdentity = 5;
+  // Byte length of the prompt prefix that stays identical across
+  // repeated scoring calls (e.g. a classifier's option-list system
+  // prompt — everything before the per-turn probe text). Backends that
+  // snapshot state (hybrid/recurrent models cannot rewind otherwise)
+  // use it to place a reuse point exactly at the boundary, so the next
+  // call re-processes only the tokens after it. 0 means unknown.
+  int32 stable_prefix_len = 6;
 }
 
 // CandidateScore is one row in the ScoreResponse, matching by index
@@ -493,6 +500,11 @@ message ModelOptions {
   // Proxy carries the cloud-proxy backend's per-model configuration.
   // Empty for non-proxy backends.
   ProxyOptions Proxy = 74;
+
+  // EnableScore reserves backend resources for the Score RPC. It is derived
+  // from the model's explicit `known_usecases: [score]` declaration so models
+  // that never score retain their ordinary serving footprint.
+  bool EnableScore = 75;
 }
 
 // ProxyOptions configures the cloud-proxy backend. UpstreamURL and

backend/cpp/bonsai/Makefile

@@ -41,6 +41,7 @@ define bonsai-build
 	# and are applied by apply-patches.sh below.
 	rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/patches
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build purge
+	bash $(LLAMA_CPP_DIR)/disable-score-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/grpc-server.cpp
 	$(info $(GREEN)I bonsai build info:$(1)$(RESET))
 	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(BONSAI_VERSION) \
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build llama.cpp
@@ -77,6 +78,7 @@ bonsai-cpu-all:
 	# and are applied by apply-patches.sh below.
 	rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/patches
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build purge
+	bash $(LLAMA_CPP_DIR)/disable-score-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/grpc-server.cpp
 	$(info $(GREEN)I bonsai build info:cpu-all-variants$(RESET))
 	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(BONSAI_VERSION) \
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build llama.cpp

backend/cpp/llama-cpp/disable-score-task.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+# Mark a copied gRPC server as targeting a llama.cpp fork that does not carry
+# LocalAI's slot-based Score patches. The RPC remains present in the shared
+# protobuf service, but responds with UNIMPLEMENTED instead of referencing
+# server task types and common_params fields absent from those forks.
+
+set -euo pipefail
+
+if [[ $# -ne 1 ]]; then
+    echo "usage: $0 <grpc-server.cpp>" >&2
+    exit 2
+fi
+
+SRC=$1
+
+if [[ ! -f "$SRC" ]]; then
+    echo "grpc-server.cpp not found at $SRC" >&2
+    exit 2
+fi
+
+if grep -q '^#define LOCALAI_LLAMA_CPP_NO_SCORE_TASK' "$SRC"; then
+    echo "==> $SRC already disables the LocalAI score task, skipping"
+    exit 0
+fi
+
+awk '
+    !done && /^#include/ {
+        print "#define LOCALAI_LLAMA_CPP_NO_SCORE_TASK 1"
+        print "// ^ injected by disable-score-task.sh for an unpatched llama.cpp fork"
+        print ""
+        done = 1
+    }
+    { print }
+    END {
+        if (!done) {
+            print "disable-score-task.sh: no #include anchor found" > "/dev/stderr"
+            exit 1
+        }
+    }
+' "$SRC" > "$SRC.tmp"
+mv "$SRC.tmp" "$SRC"
+
+echo "==> LocalAI score task disabled in $SRC"