chore(deps): bump llama.cpp to '1d36b3670b285e69e58b9d687c770a2a0a192194 (#5307)

chore(deps): bump llama.cpp to '1d36b3670b285e69e58b9d687c770a2a0a192194'

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

.env

@@ -76,7 +76,7 @@
 
 ### Define a list of GRPC Servers for llama-cpp workers to distribute the load
 # https://github.com/ggerganov/llama.cpp/pull/6829
-# https://github.com/ggerganov/llama.cpp/blob/master/examples/rpc/README.md
+# https://github.com/ggerganov/llama.cpp/blob/master/tools/rpc/README.md
 # LLAMACPP_GRPC_SERVERS=""
 
 ### Enable to run parallel requests

Makefile

@@ -6,7 +6,7 @@ BINARY_NAME=local-ai
 DETECT_LIBS?=true
 
 # llama.cpp versions
-CPPLLAMA_VERSION?=d7a14c42a1883a34a6553cbfe30da1e1b84dfd6a
+CPPLLAMA_VERSION?=1d36b3670b285e69e58b9d687c770a2a0a192194
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp

backend/cpp/llama/Makefile

@@ -59,8 +59,8 @@ llama.cpp:
 	git checkout -b build $(LLAMA_VERSION) && \
 	git submodule update --init --recursive --depth 1 --single-branch
 
-llama.cpp/examples/grpc-server: llama.cpp
-	mkdir -p llama.cpp/examples/grpc-server
+llama.cpp/tools/grpc-server: llama.cpp
+	mkdir -p llama.cpp/tools/grpc-server
 	bash prepare.sh
 
 rebuild:
@@ -70,13 +70,13 @@ rebuild:
 
 purge:
 	rm -rf llama.cpp/build
-	rm -rf llama.cpp/examples/grpc-server
+	rm -rf llama.cpp/tools/grpc-server
 	rm -rf grpc-server
 
 clean: purge
 	rm -rf llama.cpp
 
-grpc-server: llama.cpp llama.cpp/examples/grpc-server
+grpc-server: llama.cpp llama.cpp/tools/grpc-server
 	@echo "Building grpc-server with $(BUILD_TYPE) build type and $(CMAKE_ARGS)"
 ifneq (,$(findstring sycl,$(BUILD_TYPE)))
 	+bash -c "source $(ONEAPI_VARS); \

backend/cpp/llama/grpc-server.cpp

@@ -52,7 +52,7 @@ struct server_params
 {
     std::string hostname = "127.0.0.1";
     std::vector<std::string> api_keys;
-    std::string public_path = "examples/server/public";
+    std::string public_path = "tools/server/public";
     std::string chat_template = "";
     int32_t port = 8080;
     int32_t read_timeout = 600;

backend/cpp/llama/patches/01-llava.patch

@@ -1,7 +1,7 @@
-diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
+diff --git a/tools/llava/clip.cpp b/tools/llava/clip.cpp
 index 3cd0d2fa..6c5e811a 100644
---- a/examples/llava/clip.cpp
-+++ b/examples/llava/clip.cpp
+--- a/tools/llava/clip.cpp
++++ b/tools/llava/clip.cpp
 @@ -2608,7 +2608,7 @@ bool clip_image_batch_encode(clip_ctx * ctx, const int n_threads, const clip_ima
                  struct ggml_tensor * patches = ggml_graph_get_tensor(gf, "patches");
                  int* patches_data = (int*)malloc(ggml_nbytes(patches));

backend/cpp/llama/prepare.sh

@@ -7,22 +7,22 @@ for patch in $(ls patches); do
     patch -d llama.cpp/ -p1 < patches/$patch
 done 
 
-cp -r CMakeLists.txt llama.cpp/examples/grpc-server/
-cp -r grpc-server.cpp llama.cpp/examples/grpc-server/
-cp -rfv json.hpp llama.cpp/examples/grpc-server/
-cp -rfv utils.hpp llama.cpp/examples/grpc-server/
+cp -r CMakeLists.txt llama.cpp/tools/grpc-server/
+cp -r grpc-server.cpp llama.cpp/tools/grpc-server/
+cp -rfv json.hpp llama.cpp/tools/grpc-server/
+cp -rfv utils.hpp llama.cpp/tools/grpc-server/
     
-if grep -q "grpc-server" llama.cpp/examples/CMakeLists.txt; then
+if grep -q "grpc-server" llama.cpp/tools/CMakeLists.txt; then
     echo "grpc-server already added"
 else
-    echo "add_subdirectory(grpc-server)" >> llama.cpp/examples/CMakeLists.txt
+    echo "add_subdirectory(grpc-server)" >> llama.cpp/tools/CMakeLists.txt
 fi
 
 ## XXX: In some versions of CMake clip wasn't being built before llama.
 ## This is an hack for now, but it should be fixed in the future.
-cp -rfv llama.cpp/examples/llava/clip.h llama.cpp/examples/grpc-server/clip.h
-cp -rfv llama.cpp/examples/llava/clip-impl.h llama.cpp/examples/grpc-server/clip-impl.h
-cp -rfv llama.cpp/examples/llava/llava.cpp llama.cpp/examples/grpc-server/llava.cpp
-echo '#include "llama.h"' > llama.cpp/examples/grpc-server/llava.h
-cat llama.cpp/examples/llava/llava.h >> llama.cpp/examples/grpc-server/llava.h
-cp -rfv llama.cpp/examples/llava/clip.cpp llama.cpp/examples/grpc-server/clip.cpp
+cp -rfv llama.cpp/tools/llava/clip.h llama.cpp/tools/grpc-server/clip.h
+cp -rfv llama.cpp/tools/llava/clip-impl.h llama.cpp/tools/grpc-server/clip-impl.h
+cp -rfv llama.cpp/tools/llava/llava.cpp llama.cpp/tools/grpc-server/llava.cpp
+echo '#include "llama.h"' > llama.cpp/tools/grpc-server/llava.h
+cat llama.cpp/tools/llava/llava.h >> llama.cpp/tools/grpc-server/llava.h
+cp -rfv llama.cpp/tools/llava/clip.cpp llama.cpp/tools/grpc-server/clip.cpp

backend/cpp/llama/utils.hpp

@@ -1,4 +1,4 @@
-// https://github.com/ggerganov/llama.cpp/blob/master/examples/server/utils.hpp
+// https://github.com/ggerganov/llama.cpp/blob/master/tools/server/utils.hpp
 
 #pragma once