SqueezeAILab/LLMCompiler
LLMCompiler automatically computes optimized task dependency graphs to enable parallel function calling with LLMs.
Not currently ranked — collecting fresh signals.
star history
LLMCompiler is a framework for efficient and effective orchestration of parallel function calling with LLMs. It automatically decomposes problems into tasks, identifies which can run in parallel and which are interdependent, and computes optimized execution plans. It supports both open-source models (LLaMA) and closed-source models (GPT), providing latency speedup, cost savings, and accuracy improvements over sequential approaches.
Frequently asked
- What is SqueezeAILab/LLMCompiler?
- LLMCompiler automatically computes optimized task dependency graphs to enable parallel function calling with LLMs.
- Is LLMCompiler open source?
- Yes — SqueezeAILab/LLMCompiler is open source, released under the MIT license.
- What language is LLMCompiler written in?
- SqueezeAILab/LLMCompiler is primarily written in Python.
- How popular is LLMCompiler?
- SqueezeAILab/LLMCompiler has 1.9k stars on GitHub.
- Where can I find LLMCompiler?
- SqueezeAILab/LLMCompiler is on GitHub at https://github.com/SqueezeAILab/LLMCompiler.