enhancementgood first issue
Repository metrics
- Stars
- (52,968 個のスター)
- PR merge metrics
- (平均マージ 5d 20h) (30d で 36 merged PRs)
説明
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 This would make the benchmarks in #89 outdated, but would make future benchmarks more realistic.