llm-inspector is an open-source CLI tool that provides real-time monitoring and observability for large language model (LLM) inference. It offers detailed metrics on inference performance, GPU usage, and supports various LLM backends such as Ollama and vLLM. Designed for machine learning engineers seeking insight into LLM operations.
In the LLM eval & observability space, llm-inspector takes a focused approach. It focuses on monitoring and measuring the performance of large language model inference in real time. llm-inspector is an open-source project aimed at machine learning engineers. llm-inspector is open source under the MIT license. llm-inspector is available on the command line.
It is developed by Helasaoudi, and it first shipped in 2026. Among its 5 catalogued features are LLM monitoring, inference metrics, and GPU usage.
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