Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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 Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ DETECT_LIBS?=true
# llama.cpp versions
GOLLAMA_REPO?=https://github.com/go-skynet/go-llama.cpp
GOLLAMA_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
CPPLLAMA_VERSION?=cce5a9007572c6e9fa522296b77571d2e5071357
CPPLLAMA_VERSION?=47f931c8f9a26c072d71224bc8013cc66ea9e445

# go-rwkv version
RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp
Expand Down
4 changes: 2 additions & 2 deletions backend/cpp/llama/grpc-server.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -203,7 +203,7 @@ struct llama_client_slot
std::string stopping_word;

// sampling
struct common_sampler_params sparams;
struct common_params_sampling sparams;
common_sampler *ctx_sampling = nullptr;

int32_t ga_i = 0; // group-attention state
Expand Down Expand Up @@ -662,7 +662,7 @@ struct llama_server_context

bool launch_slot_with_data(llama_client_slot* &slot, json data) {
slot_params default_params;
common_sampler_params default_sparams;
common_params_sampling default_sparams;

slot->params.stream = json_value(data, "stream", false);
slot->params.cache_prompt = json_value(data, "cache_prompt", false);
Expand Down