vllm-project / vllm-project/production-stack

Question about `tolerations` in `servingEngineSpec`

Open
#294 4 comments 4 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Python
Stars
2.6k
Forks
503
Avg merge
4d 17h
Merged PRs (30d)
8

Description

In many cases, tolerations property is used together with nodeSelectorTerms.
However it seems tolerations is in servingEngineSpec while nodeSelectorTerms is in modelSpec.
I think it would be great the two properties are in the same section one of either servingEngineSpec or modelSpec.
Since those properties are applied per node, it would be better to have it in modelSpec I guess?
The downside might be the modelSpec could be too verbose.
On the other hand, it could cover the case where each model could be deployed to different tainted Nodes with different labels.

Could you consider this case?

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 by locating the definitions and usage of servingEngineSpec, modelSpec, tolerations, and nodeSelectorTerms. Review how these properties are applied to Kubernetes workloads, then determine whether moving tolerations enables per-model node placement without making modelSpec excessively verbose; done means an agreed configuration design and corresponding behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
kubernetes
Domain
infrastructure
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.