openvinotoolkit / openvinotoolkit/model_server

Queue policy

Open
#2,543 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
C++
Stars
931
Forks
277
Avg merge
2d 13h
Merged PRs (30d)
68

Description

Can OVMS support modifying the queue policy, for example by supporting priority levels? For example, when OVMS is serving multiple models, it might make sense to support different priority levels for each model, so that more resources can be dedicated to those with higher priority levels. I believe Triton is also supporting such feature.

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

No OVMS files, tests, or entry points are mentioned. Start by reviewing the Triton model configuration documentation linked in the issue and the server's multi-model queueing design. Done means defining and implementing a clear policy for model priority levels and verifying that higher-priority models receive the intended resource preference.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
ai-infra-agents
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.