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

bug: enable and fix the cache again #480

Merged
merged 2 commits into from
Apr 4, 2024
Merged

bug: enable and fix the cache again #480

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
2c25ffc
bug: enable and fix the cache again
tikikun Apr 4, 2024
dc77ce1
bug: clean kv cache must be false all the time
tikikun Apr 4, 2024
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
3 changes: 1 addition & 2 deletions context/llama_server_context.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -471,7 +471,7 @@ struct llama_server_context {
llama_batch batch;

bool multimodal = false;
bool clean_kv_cache = true;
bool clean_kv_cache = false;
bool all_slots_are_idle = false;
bool add_bos_token = true;

Expand Down Expand Up @@ -860,7 +860,6 @@ struct llama_server_context {
void kv_cache_clear() {
// clear the entire KV cache
llama_kv_cache_clear(ctx);
clean_kv_cache = false;
}

void update_system_prompt() {
Expand Down
2 changes: 1 addition & 1 deletion controllers/llamaCPP.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -615,7 +615,7 @@ bool llamaCPP::LoadModelImpl(std::shared_ptr<Json::Value> jsonBody) {
params.cont_batching = jsonBody->get("cont_batching", false).asBool();
this->clean_cache_threshold =
jsonBody->get("clean_cache_threshold", 5).asInt();
this->caching_enabled = jsonBody->get("caching_enabled", false).asBool();
this->caching_enabled = jsonBody->get("caching_enabled", true).asBool();
this->user_prompt = jsonBody->get("user_prompt", "USER: ").asString();
this->ai_prompt = jsonBody->get("ai_prompt", "ASSISTANT: ").asString();
this->system_prompt =
Expand Down