vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama/ex: remove --logdir argument (#10339)

Browse source
This commit is contained in:
Johannes Gäßler 2024-11-16 23:00:41 +01:00 • committed by GitHub
parent db4cfd5dbc
commit 4e54be0ec6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 0 additions and 547 deletions
Download patch file Download diff file Expand all files Collapse all files

22
src/llama.cpp
View file

@ -22075,28 +22075,6 @@ void llama_perf_context_reset(struct llama_context * ctx) {
ctx->t_p_eval_us = ctx->n_p_eval = 0;
}
void llama_perf_dump_yaml(FILE * stream, const llama_context * ctx) {
fprintf(stream, "\n");
fprintf(stream, "###########\n");
fprintf(stream, "# Timings #\n");
fprintf(stream, "###########\n");
fprintf(stream, "\n");
fprintf(stream, "mst_eval: %.2f # ms / token during generation\n",
1.0e-3 * ctx->t_eval_us / ctx->n_eval);
fprintf(stream, "mst_p_eval: %.2f # ms / token during prompt processing\n",
1.0e-3 * ctx->t_p_eval_us / ctx->n_p_eval);
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, "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, "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",
1.0e6 * ctx->n_p_eval / ctx->t_p_eval_us);
}
// For internal test use
const std::vector<std::pair<std::string, struct ggml_tensor *>> & llama_internal_get_tensor_map(
struct llama_context * ctx