chore(deps): bump llama.cpp to '835b2b915c52bcabcd688d025eacff9a07b65f52' (#6347)

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

Author: mudler

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=4ae88d07d026e66b41e85afece74e88af54f4e66
+LLAMA_VERSION?=835b2b915c52bcabcd688d025eacff9a07b65f52
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/grpc-server.cpp

@@ -802,11 +802,6 @@ class BackendServiceImpl final : public backend::Backend::Service {
             return grpc::Status(grpc::StatusCode::INVALID_ARGUMENT, "\"documents\" must be a non-empty string array");
         }
 
-        // Tokenize the query
-        auto tokenized_query = tokenize_input_prompts(ctx_server.vocab, ctx_server.mctx, request->query(), /* add_special */ false, true);
-        if (tokenized_query.size() != 1) {
-            return grpc::Status(grpc::StatusCode::INVALID_ARGUMENT, "\"query\" must contain only a single prompt");
-        }
         // Create and queue the task
         json responses = json::array();
         bool error = false;
@@ -818,10 +813,9 @@ class BackendServiceImpl final : public backend::Backend::Service {
                 documents.push_back(request->documents(i));
             }
 
-            auto tokenized_docs = tokenize_input_prompts(ctx_server.vocab, ctx_server.mctx, documents, /* add_special */ false, true);
-            tasks.reserve(tokenized_docs.size());
-            for (size_t i = 0; i < tokenized_docs.size(); i++) {
-                auto tmp = format_rerank(ctx_server.vocab, tokenized_query[0], tokenized_docs[i]);
+            tasks.reserve(documents.size());
+            for (size_t i = 0; i < documents.size(); i++) {
+                auto tmp = format_rerank(ctx_server.model, ctx_server.vocab, ctx_server.mctx, request->query(), documents[i]);
                 server_task task = server_task(SERVER_TASK_TYPE_RERANK);
                 task.id = ctx_server.queue_tasks.get_new_id();
                 task.index = i;