llm-d is an open-source, high-performance distributed inference serving stack designed for deploying large language models on various hardware accelerators. It provides orchestration, optimization, and benchmarking tools for production ML inference, targeting ML engineers and infrastructure teams.
In the AI space, llm-d takes a focused approach. It simplifies and optimizes the deployment of large language models for high-performance inference on diverse hardware. llm-d is an open-source project aimed at machine learning engineers. The project is open source (Apache-2.0). It ships for the web, the command line, and API, and it can be self-hosted.
Behind llm-d is CNCF (Red Hat, Google Cloud, IBM Research, CoreWeave, NVIDIA), and it first shipped in 2025. Development happens publicly on GitHub with 3.5k stars and 530 commits in the last 90 days. Among its 5 catalogued features are distributed inference, kubernetes support, and model orchestration.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do