diff options
Diffstat (limited to 'llama.cpp')
| -rw-r--r-- | llama.cpp | 9 |
1 files changed, 4 insertions, 5 deletions
@@ -6248,7 +6248,6 @@ const char * llama_print_system_info(void) { } void llama_dump_timing_info_yaml(FILE * stream, const llama_context * ctx) { - fprintf(stream, "\n"); fprintf(stream, "###########\n"); fprintf(stream, "# Timings #\n"); @@ -6264,10 +6263,10 @@ void llama_dump_timing_info_yaml(FILE * stream, const llama_context * ctx) { fprintf(stream, "n_eval: %d # number of tokens generated (excluding the first one)\n", ctx->n_eval); fprintf(stream, "n_p_eval: %d # number of tokens processed in batches at the beginning\n", ctx->n_p_eval); fprintf(stream, "n_sample: %d # number of sampled tokens\n", ctx->n_sample); - fprintf(stream, "t_eval_us: %ld # total microseconds spent generating tokens\n", ctx->t_eval_us); - fprintf(stream, "t_load_us: %ld # total microseconds spent loading the model\n", ctx->t_load_us); - fprintf(stream, "t_p_eval_us: %ld # total microseconds spent prompt processing\n", ctx->t_p_eval_us); - fprintf(stream, "t_sample_us: %ld # total microseconds spent sampling\n", ctx->t_sample_us); + fprintf(stream, "t_eval_us: %" PRId64 " # total microseconds spent generating tokens\n", ctx->t_eval_us); + fprintf(stream, "t_load_us: %" PRId64 " # total microseconds spent loading the model\n", ctx->t_load_us); + fprintf(stream, "t_p_eval_us: %" PRId64 " # total microseconds spent prompt processing\n", ctx->t_p_eval_us); + fprintf(stream, "t_sample_us: %" PRId64 " # total microseconds spent sampling\n", ctx->t_sample_us); fprintf(stream, "ts_eval: %.2f # tokens / second during generation\n", 1.0e6 * ctx->n_eval / ctx->t_eval_us); fprintf(stream, "ts_p_eval: %.2f # tokens / second during prompt processing\n", |