Hyunjae Woo

Before After Should we keep some precisions for both accuracy as well as aesthetic? (columns seem a bit too narrow 😅) I know @dyastremsky argued for integral number for nanosecond...

Closing the draft as the functionality is implemented and merged through the following PRs: - #767 - https://github.com/triton-inference-server/perf_analyzer/pull/33

Hi @ZhanqiuHu, > I am trying to profile our decoupled models (python backend) with perf_analyzer, and I'm curious how the following latency metrics are calculated? Please see [here](https://github.com/triton-inference-server/client/blob/main/src/c%2B%2B/perf_analyzer/docs/measurements_metrics.md#metrics) for the...

For `compute input`, `compute infer`, and `compute output` metrics, you could read the Triton doc [here](https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/user_guide/metrics.html#counters) for more details. > When I use -i grpc the flag, it doesn't seem...

> If I want to pass specific data to perf analyzer using --input-data passing json in this pattern, but getting error : Failed to init manager inputs: unable to find...

hi @Kanupriyagoyal try this: ```json { "data": [ { "IN0": { "content": ["17", "2", "2007", "6", "30", "16", "15", "0", "5.4", "Swipe Transaction", "-6571010470072147219", "Bloomville", "OH", "44818", "5499", "Bad PIN"],...

Hi @mirekphd opened a ticket TMA-1955 to track the issue.