interestingLSY/swiftLLM

A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

44
/ 100
Emerging

This project offers a specialized system for experimenting with large language models (LLMs). It takes in LLM weights (like LLaMA variants) and provides high-performance inference outputs, similar to production systems, but within a much smaller, easier-to-modify codebase. It's designed for LLM researchers who need to test novel scheduling or attention mechanisms efficiently.

320 stars. No commits in the last 6 months.

Use this if you are an LLM researcher or academic who needs to rapidly prototype and test new ideas for improving LLM inference performance or explore different architectural components without wading through complex, feature-rich production codebases.

Not ideal if you need a full-featured, production-ready LLM serving solution with broad model and hardware support, or features like quantization, LoRA, and multimodal capabilities out-of-the-box.

LLM-research AI-experimentation model-inference-optimization deep-learning-prototyping
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

320

Forks

35

Language

Python

License

Apache-2.0

Last pushed

Jun 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/interestingLSY/swiftLLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.