Skip to content

Efficient LLM Inference using vLLM #29

Description

@at-ay

Project Description

The main goal of this project is to evaluate the performance of vLLM (https://github.com/vllm-project/vllm) for LLM inference tasks. In order to achieve this, the student should read some related papers (The first one should be this -> https://arxiv.org/abs/2309.06180) and get her/his hand dirty with vLLM installations.
The ultimate aim is to create an experiment testbed where users can execute parametric and repeatable experiments for trying out different LLMs and reporting their performance.

Metadata

Metadata

Assignees

Labels

ai/mlcan machines think?software engineeringRequirements, Design, Architecture, Implementation, Testing

Type

No type

Projects

Status
Offered

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions