Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 26, 2025
Merged

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

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 backend/cpp/llama-cpp/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@

LLAMA_VERSION?=4ae88d07d026e66b41e85afece74e88af54f4e66
LLAMA_VERSION?=835b2b915c52bcabcd688d025eacff9a07b65f52
LLAMA_REPO?=https://github.com/ggerganov/llama.cpp

CMAKE_ARGS?=
Expand Down
12 changes: 3 additions & 9 deletions backend/cpp/llama-cpp/grpc-server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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;
Expand All @@ -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;
Expand Down
Loading