fix(llama-cpp): normalize batch threads

The updated llama.cpp creates its batch threadpool during model initialization, before the context-level fallback can replace the -1 sentinel. Resolve that sentinel from the inference thread count so model loading does not overflow the threadpool allocation.\n\nAssisted-by: Codex:gpt-5.4

Author: localai-org-maint-bot

backend/cpp/llama-cpp/CMakeLists.txt

@@ -120,4 +120,9 @@ if(LLAMA_GRPC_BUILD_TESTS)
     target_include_directories(tts_request_options_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
     target_compile_features(tts_request_options_test PRIVATE cxx_std_17)
     add_test(NAME tts_request_options_test COMMAND tts_request_options_test)
+
+    add_executable(thread_params_test thread_params_test.cpp thread_params.h)
+    target_include_directories(thread_params_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
+    target_compile_features(thread_params_test PRIVATE cxx_std_17)
+    add_test(NAME thread_params_test COMMAND thread_params_test)
 endif()

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

@@ -53,6 +53,7 @@
 #include "arg.h"
 #include "chat-auto-parser.h"
 #include "llama_compat.h" // fork-skew switches, generated by prepare.sh
+#include "thread_params.h"
 #include "message_content.h"
 #include "passthrough_options.h"
 #include "tts_request_options.h"
@@ -1412,6 +1413,12 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
             passthrough_draft_gpu_layers);
     }
 
+    // The library initializer now creates both threadpools before the server
+    // can apply llama_context's fallback for the -1 batch-thread sentinel.
+    params.cpuparams_batch.n_threads = llama_grpc::resolve_batch_threads(
+        params.cpuparams_batch.n_threads,
+        params.cpuparams.n_threads);
+
 #ifndef LOCALAI_LLAMA_CPP_NO_SCORE_TASK
     // Score-task suffix forking: reserve seq ids (and recurrent-state cells)
     // beyond the slots so one scoring call decodes all candidate tails in a

backend/cpp/llama-cpp/prepare.sh

@@ -32,6 +32,9 @@ cp -r passthrough_options_test.cpp llama.cpp/tools/grpc-server/
 # regression test.
 cp -r tts_request_options.h llama.cpp/tools/grpc-server/
 cp -r tts_request_options_test.cpp llama.cpp/tools/grpc-server/
+# Thread-count default normalization and its standalone regression test.
+cp -r thread_params.h llama.cpp/tools/grpc-server/
+cp -r thread_params_test.cpp llama.cpp/tools/grpc-server/
 # Parent-death watcher (included by grpc-server.cpp) and its standalone unit
 # test (run via backend/cpp/run-unit-tests.sh; also buildable under ctest).
 cp -r parent_watch.h llama.cpp/tools/grpc-server/

backend/cpp/llama-cpp/thread_params.h

@@ -0,0 +1,11 @@
+#pragma once
+
+#include <cstdint>
+
+namespace llama_grpc {
+
+inline int32_t resolve_batch_threads(int32_t batch_threads, int32_t inference_threads) {
+    return batch_threads < 0 ? inference_threads : batch_threads;
+}
+
+} // namespace llama_grpc

backend/cpp/llama-cpp/thread_params_test.cpp

@@ -0,0 +1,15 @@
+#include "thread_params.h"
+
+#include <cstdio>
+
+int main() {
+    if (llama_grpc::resolve_batch_threads(-1, 4) != 4) {
+        std::fprintf(stderr, "default batch threads did not inherit inference threads\n");
+        return 1;
+    }
+    if (llama_grpc::resolve_batch_threads(2, 4) != 2) {
+        std::fprintf(stderr, "explicit batch threads were overwritten\n");
+        return 1;
+    }
+    return 0;
+}