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

Suggestion to reduce RAM consumption

Open
#5,259 12 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Is your feature request related to a problem? Please describe.
So I'm trying to use tritonserver in my project. But it uses a lot of RAM for a single model.

  • Is this expected behaviour?
  • Are there any tricks to reduce RAM consumption?

Describe the solution you'd like
I'd like to collect list of tips and trick that actually helps to reduce memory footprint.

Describe alternatives you've considered
I've rigorously checked documentation and github issues.

Additional context
My setup looks like as follows: EC2 g4dn.large (4 vCPU, 16 RAM, Nvidia T4). While deploying model consumes like 10Gb of RAM.
Should I consider using instances with more RAM?

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 reviewing the Triton documentation and GitHub issues referenced by the reporter, then examine the stated EC2 g4dn.large deployment and its roughly 10 GB RAM use. Done would mean a decided, actionable collection of memory-reduction tips and an explanation of whether this consumption is expected or requires a larger instance.

Written by the indexing model from the issue text.

Assessment

Tech stack
aws, machine-learning
Domain
cloud, machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.