triton-inference-server / triton-inference-server/server

support decoupled mode in perf_analyzer

Open
#4,530 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Enhancement
Dominant language
Python
Stars
11k
Forks
1.8k
Avg merge
3d 16h
Merged PRs (30d)
28

Description

when using perf_analyzer to analyze a python decoupled model like triton-decoupled using command below

perf_analyzer -i grpc --streaming -m repeat --concurrency-range 1:2  -vv --input-data repeat_data.json

repeat_data.json

  {
    "data" :
     [
        {
          "IN" : [5]
        }
      ]
  }

which 5 means how many response will server (decouple mode) will send to client

the results will show error

No valid requests recorded within time interval. Please use a larger time window.

it seems like perf_analyzer will send a request when it get a response, but in decouple mode, perf_analyzer should not send request again until it get final response from decouple mode

Contributor guide

Open the contributing guide

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 the perf_analyzer CLI command and repeat_data.json shown in the issue, reproducing it against the linked triton-decoupled Python model. Trace how streaming responses are handled, then verify that five decoupled responses complete as one request and that the reported time-window error no longer occurs.

Written by the indexing model from the issue text.

Assessment

Tech stack
grpc, python
Domain
cli, tooling
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 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.