ggml-org/whisper.cpp

Should we use process time for benchmarks/timings?

Offen

#382 geöffnet am 07.01.2023

 (2 Kommentare) (0 Reaktionen) (0 zugewiesene Personen)C++ (6.072 Forks)batch import
enhancementgood first issue

Repository-Metriken

Stars
 (52.942 Sterne)
PR-Merge-Metriken
 (Durchschn. Merge 5T 20h) (36 gemergte PRs in 30 T)

Beschreibung

Currently, the bench tool simply spits out the timings from whisper_print_timings. These timings are not process specific and as such are influenced by other processes on the system.

Should we use something like CLOCK_PROCESS_CPUTIME_ID instead of CLOCK_MONOTONIC in ggml_time_*? This would make the benchmarks in #89 outdated, but would make future benchmarks more realistic.

Contributor Guide