Skip to content

server : fix metrics init #5964

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
Mar 9, 2024
Merged

server : fix metrics init #5964

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
17 changes: 12 additions & 5 deletions examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -341,7 +341,7 @@ struct server_slot {
};

struct server_metrics {
const int64_t t_start = ggml_time_us();
int64_t t_start = 0;

uint64_t n_prompt_tokens_processed_total = 0;
uint64_t t_prompt_processing_total = 0;
Expand All @@ -354,14 +354,18 @@ struct server_metrics {
uint64_t n_tokens_predicted = 0;
uint64_t t_tokens_generation = 0;

void on_prompt_eval(const server_slot &slot) {
void init() {
t_start = ggml_time_us();
}

void on_prompt_eval(const server_slot & slot) {
n_prompt_tokens_processed_total += slot.n_prompt_tokens_processed;
n_prompt_tokens_processed += slot.n_prompt_tokens_processed;
t_prompt_processing += slot.t_prompt_processing;
t_prompt_processing_total += slot.t_prompt_processing;
}

void on_prediction(const server_slot &slot) {
void on_prediction(const server_slot & slot) {
n_tokens_predicted_total += slot.n_decoded;
n_tokens_predicted += slot.n_decoded;
t_tokens_generation += slot.t_token_generation;
Expand Down Expand Up @@ -690,10 +694,11 @@ struct server_context {
return res > 0;
}

void initialize() {
void init() {
const int32_t n_ctx_slot = n_ctx / params.n_parallel;

LOG_INFO("initializing slots", {{"n_slots", params.n_parallel}});

for (int i = 0; i < params.n_parallel; i++) {
server_slot slot;

Expand Down Expand Up @@ -735,6 +740,8 @@ struct server_context {
default_generation_settings_for_props["seed"] = -1;

batch = llama_batch_init(n_ctx, 0, params.n_parallel);

metrics.init();
}

std::vector<llama_token> tokenize(const json & json_prompt, bool add_bos) const {
Expand Down Expand Up @@ -2783,7 +2790,7 @@ int main(int argc, char ** argv) {
state.store(SERVER_STATE_ERROR);
return 1;
} else {
ctx_server.initialize();
ctx_server.init();
state.store(SERVER_STATE_READY);
}

Expand Down