LLMCompiler
LLMCompiler is a compiler framework for parallel function calls.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 1.9k
- Source
- GitHub
- Added
- 2026-06-07
- Last verified
- 2026-06-07
Overview
LLMCompiler is a compiler framework for parallel function calls that can automatically identify which tasks can be executed in parallel and which are interdependent. It addresses high latency, high cost, and inaccurate behavior issues in current multi-function call methods caused by sequential reasoning and execution. Users only need to specify tools and related examples, and LLMCompiler will automatically compute an optimized function call plan. It supports both open-source models such as LLaMA and closed-source models like OpenAI's GPT series.
Key features
- ▪Supports parallel function calls
- ▪Automatically identifies task dependencies
- ▪Reduces latency and cost
- ▪Improves accuracy
Use cases
Pros
- ＋Efficient task scheduling
- ＋Compatible with multiple models
- ＋Easy to integrate and use
Limitations / notes
- －Requires environment configuration
- －May need adjustments for certain models
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
How do I install LLMCompiler?
Create a conda environment, clone the repository, and install dependencies.
Which models are supported?
Supports open-source and closed-source models such as LLaMA, GPT, etc.
Something wrong? Let us know on the About page and we'll fix it.