Skip to content
This repository was archived by the owner on Jul 4, 2025. It is now read-only.

hotfix: update bug fixes for recent batch inference #109

Merged
merged 2 commits into from
Nov 7, 2023
Merged

hotfix: update bug fixes for recent batch inference #109

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
838011e
pump version
tikikun Nov 7, 2023
131359e
feat: fix embedding bug
tikikun Nov 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ add_executable(${PROJECT_NAME} main.cc)
#
# and comment out the following lines
find_package(Drogon CONFIG REQUIRED)
target_link_libraries(${PROJECT_NAME} PRIVATE Drogon::Drogon common llama clip
target_link_libraries(${PROJECT_NAME} PRIVATE Drogon::Drogon common llama llava
${CMAKE_THREAD_LIBS_INIT})

# ##############################################################################
Expand Down
8 changes: 4 additions & 4 deletions controllers/llamaCPP.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,7 @@ void llamaCPP::chatCompletion(
data["stop"] = stopWords;
}

const int task_id = llama.request_completion(data, false);
const int task_id = llama.request_completion(data, false,false);
LOG_INFO << "Resolved request for task_id:" << task_id;

auto state = createState(task_id, this);
Expand Down Expand Up @@ -178,7 +178,7 @@ void llamaCPP::embedding(
prompt = "";
}
const int task_id =
llama.request_completion({{"prompt", prompt}, {"n_predict", 0}}, false);
llama.request_completion({{"prompt", prompt}, {"n_predict", 0}}, false, true);
task_result result = llama.next_result(task_id);
std::string embeddingResp = result.result_json.dump();
auto resp = nitro_utils::nitroHttpResponse();
Expand Down Expand Up @@ -226,8 +226,8 @@ void llamaCPP::loadModel(

llama_backend_init(params.numa);

LOG_INFO_LLAMA("build info",
{{"build", BUILD_NUMBER}, {"commit", BUILD_COMMIT}});
// LOG_INFO_LLAMA("build info",
// {{"build", BUILD_NUMBER}, {"commit", BUILD_COMMIT}});
LOG_INFO_LLAMA("system info",
{
{"n_threads", params.n_threads},
Expand Down
Loading