enhancementgood first issue
倉庫指標
- 星標
- (52,968 顆星)
- PR 合併指標
- (平均合併 5天 20小時) (30 天內合併 36 個 PR)
描述
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 This would make the benchmarks in #89 outdated, but would make future benchmarks more realistic.