SqueezeAILab/LLMCompiler

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

44
/ 100
Emerging

This project helps developers integrate large language models (LLMs) with custom tools or functions more efficiently. It automatically figures out which tasks an LLM needs to perform using these tools can run at the same time and which ones depend on each other. Developers provide the LLM with a set of tools and example prompts, and the project optimizes how the LLM calls these tools to complete complex problems faster and more accurately. This is for developers building applications that use LLMs to solve problems that require multiple steps and external data or computations.

1,828 stars. No commits in the last 6 months.

Use this if you are a developer building LLM-powered applications and want to improve the speed, cost-efficiency, and accuracy of multi-function calling by enabling parallel execution of tasks.

Not ideal if you are looking for an off-the-shelf application to solve a specific problem, as this is a framework for developers to build with.

LLM application development AI workflow orchestration API integration Developer tools Software engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

1,828

Forks

126

Language

Python

License

MIT

Last pushed

Jul 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SqueezeAILab/LLMCompiler"

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