NVIDIA / NVIDIA/TensorRT-LLM

[AutoDeploy]: investigate and improve single-GPU performance on select models

Open
#7,047 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

AutoDeploy
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

🚀 The feature, motivation and pitch

Single GPU is on average 20% slower than the manual torch reference.
Select a small list of models and improve them

Alternatives

No response

Additional context

No response

Before submitting a new issue...
  • Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

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 files, tests, or specific models are named. Start by reproducing the single-GPU AutoDeploy measurements and comparing them with the manual torch reference across a small model list; done means the selected models show improved performance and the comparison is documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
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.