ggml-org/whisper.cpp

Should we use process time for benchmarks/timings?

Aperta

#382 aperta il 7 gen 2023

 (2 commenti) (0 reazioni) (0 assegnatari)C++ (6072 fork)batch import
enhancementgood first issue

Metriche repository

Star
 (52.942 stelle)
Metriche merge PR
 (Merge medio 5g 20h) (36 PR mergiate in 30 g)

Descrizione

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 This would make the benchmarks in #89 outdated, but would make future benchmarks more realistic.

Guida contributor