ggml-org/whisper.cpp

Should we use process time for benchmarks/timings?

Aberta

#382 aberto em 7 de jan. de 2023

 (2 comentários) (0 reação) (0 responsável)C++ (6.074 forks)batch import
enhancementgood first issue

Métricas do repositório

Stars
 (52.968 estrelas)
Métricas de merge de PR
 (Mesclagem média 5d 20h) (36 fundiu PRs em 30d)

Description

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 This would make the benchmarks in #89 outdated, but would make future benchmarks more realistic.

Guia do colaborador