deepspeedai / deepspeedai/DeepSpeedExamples

Throughput should be `num_queries/latency` as opposed to `num_clients/latency`?

Open
#858 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
6.8k
Forks
1.1k
Avg merge
2d 16h
Merged PRs (30d)
1

Description

The mii inferencing benchmark script computes throughput as num_clients/latency. Shouldn't this be num_queries/latency?

Also why use P95 latency and not the total time it took to process all the requests, for the purposes of computing throughput?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with benchmarks/inference/mii/src/postprocess_results.py at line 73 and trace how num_clients, num_queries, and latency are produced by the benchmark. Determine which denominator and latency measure represent throughput, then update the calculation so the reported metric matches that definition and verify the resulting output on a benchmark run.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
performance
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.