@arizeai/phoenix-mcp

--- description: >- Groq provides ultra-low latency inference for LLMs through its custom-built LPU™ architecture. --- # Groq <figure><picture><source srcset="../../.gitbook/assets/groq_white_logo.png" media="(prefers-color-scheme: dark)"><img src="../../.gitbook/assets/groq+logo.png" alt="" width="375"></picture><figcaption></figcaption></figure> **Website:** [https://groq.com/](https://groq.com/) <table data-card-size="large" data-view="cards"><thead><tr><th></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><a href="groq-tracing.md"><strong>Groq Tracing</strong></a></td><td><a href="../../.gitbook/assets/groq.avif">groq.avif</a></td></tr></tbody></table> ### Featured Tutorials <table data-view="cards"><thead><tr><th></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><a href="https://colab.research.google.com/github/Arize-ai/phoenix/blob/ac9ebede43d04c6b8b70a30356e70eb65513d715/tutorials/tracing/groq_tracing_tutorial.ipynb#L20">Tracing a Groq Application</a></td><td><a href="../../.gitbook/assets/Tutorials.jpg">Tutorials.jpg</a></td></tr></tbody></table>