root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Add timings for the prompt evaluation (#478)

Browse Source
This commit is contained in:
slaren 2023-03-25 15:34:23 +01:00 committed by GitHub
parent 4a7129acd2
commit 29b7baab67
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 13 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
llama.cpp
View File

@ -168,9 +168,11 @@ struct llama_context {
int64_t t_sample_us = 0;
int64_t t_eval_us = 0;
int64_t t_p_eval_us = 0;
int32_t n_sample = 0; // number of tokens sampled
int32_t n_eval = 0; // number of eval calls
int32_t n_p_eval = 0; // number of tokens in eval calls for the prompt (with batch size > 1)
llama_model model;
llama_vocab vocab;
@ -1070,6 +1072,10 @@ static bool llama_eval_internal(
lctx.t_eval_us += ggml_time_us() - t_start_us;
lctx.n_eval++;
}
else if (N > 1) {
lctx.t_p_eval_us += ggml_time_us() - t_start_us;
lctx.n_p_eval += N;
}
return true;
}
@ -1811,12 +1817,14 @@ void llama_print_timings(struct llama_context * ctx) {
const int32_t n_sample = std::max(1, ctx->n_sample);
const int32_t n_eval = std::max(1, ctx->n_eval);
const int32_t n_p_eval = std::max(1, ctx->n_p_eval);
fprintf(stderr, "\n");
fprintf(stderr, "%s: load time = %8.2f ms\n", __func__, ctx->t_load_us / 1000.0f);
fprintf(stderr, "%s: sample time = %8.2f ms / %5d runs (%8.2f ms per run)\n", __func__, 1e-3f * ctx->t_sample_us, n_sample, 1e-3f * ctx->t_sample_us / n_sample);
fprintf(stderr, "%s: eval time = %8.2f ms / %5d runs (%8.2f ms per run)\n", __func__, 1e-3f * ctx->t_eval_us, n_eval, 1e-3f * ctx->t_eval_us / n_eval);
fprintf(stderr, "%s: total time = %8.2f ms\n", __func__, (t_end_us - ctx->t_start_us)/1000.0f);
fprintf(stderr, "%s: load time = %8.2f ms\n", __func__, ctx->t_load_us / 1000.0f);
fprintf(stderr, "%s: sample time = %8.2f ms / %5d runs (%8.2f ms per run)\n", __func__, 1e-3f * ctx->t_sample_us, n_sample, 1e-3f * ctx->t_sample_us / n_sample);
fprintf(stderr, "%s: prompt eval time = %8.2f ms / %5d tokens (%8.2f ms per token)\n", __func__, 1e-3f * ctx->t_p_eval_us, n_p_eval, 1e-3f * ctx->t_p_eval_us / n_p_eval);
fprintf(stderr, "%s: eval time = %8.2f ms / %5d runs (%8.2f ms per run)\n", __func__, 1e-3f * ctx->t_eval_us, n_eval, 1e-3f * ctx->t_eval_us / n_eval);
fprintf(stderr, "%s: total time = %8.2f ms\n", __func__, (t_end_us - ctx->t_start_us)/1000.0f);
}
void llama_reset_timings(struct llama_context * ctx) {
@ -1824,6 +1832,7 @@ void llama_reset_timings(struct llama_context * ctx) {
ctx->t_sample_us = ctx->n_sample = 0;
ctx->t_eval_us = ctx->n_eval = 0;
ctx->t_p_eval_us = ctx->n_p_eval = 0;
}
const char * llama_print_system_info(void) {