diff --git a/backend/cpp/llama-cpp/Makefile b/backend/cpp/llama-cpp/Makefile index 290c5a360b2a..af9abd28c79f 100644 --- a/backend/cpp/llama-cpp/Makefile +++ b/backend/cpp/llama-cpp/Makefile @@ -1,5 +1,5 @@ -LLAMA_VERSION?=4abef75f2cf2eee75eb5083b30a94cf981587394 +LLAMA_VERSION?=d82b7a7c1d73c0674698d9601b1bbb0200933f29 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp CMAKE_ARGS?= diff --git a/backend/cpp/llama-cpp/grpc-server.cpp b/backend/cpp/llama-cpp/grpc-server.cpp index bd251caedf2d..52a343ac4f85 100644 --- a/backend/cpp/llama-cpp/grpc-server.cpp +++ b/backend/cpp/llama-cpp/grpc-server.cpp @@ -1199,7 +1199,7 @@ class BackendServiceImpl final : public backend::Backend::Service { task.id_slot = json_value(data, "id_slot", -1); // OAI-compat - task.params.oaicompat = OAICOMPAT_TYPE_NONE; + task.params.res_type = TASK_RESPONSE_TYPE_NONE; task.params.oaicompat_cmpl_id = completion_id; // oaicompat_model is already populated by params_from_json_cmpl @@ -1930,7 +1930,7 @@ class BackendServiceImpl final : public backend::Backend::Service { task.id_slot = json_value(data, "id_slot", -1); // OAI-compat - task.params.oaicompat = OAICOMPAT_TYPE_NONE; + task.params.res_type = TASK_RESPONSE_TYPE_NONE; task.params.oaicompat_cmpl_id = completion_id; // oaicompat_model is already populated by params_from_json_cmpl @@ -2056,7 +2056,7 @@ class BackendServiceImpl final : public backend::Backend::Service { task.index = i; task.tokens = std::move(tokenized_prompts[i]); - task.params.oaicompat = OAICOMPAT_TYPE_NONE; + task.params.res_type = TASK_RESPONSE_TYPE_NONE; task.params.embd_normalize = embd_normalize; tasks.push_back(std::move(task)); }