vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-09 19:46:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '467576b6cc' into concedo_experimental

Browse source 
# Conflicts:
#	.gitignore
#	Makefile
#	README.md
#	common/common.h
#	docs/build.md
#	examples/infill/infill.cpp
#	examples/perplexity/perplexity.cpp
#	examples/server/README.md
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.sh
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-opt.cpp
#	tests/test-quantize-perf.cpp
This commit is contained in:
Concedo 2024-11-21 16:05:21 +08:00
commit 282a647689
21 changed files with 1788 additions and 1788 deletions
Download patch file Download diff file Expand all files Collapse all files

22
src/llama.cpp
View file

@ -22252,28 +22252,6 @@ 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