Groq#

2 picked talks across 2 digests with a speaker from Groq, newest first.

MLSys 2026#

• SHIP: SRAM-Based Huge Inference Pipelines for Fast LLM Serving · Core — Andrew Bitar, Aravind Vayalapra, Baorui Zhou, et al. (Groq, per the paper — the deployment studied is Groq's public cloud)

Cisco Live US 2025 (San Diego)#

• Groq: An AI Success Story - Deploying High-Performance, and Low-Latency AI Networks Using Cisco Nexus 9000 - CSSDCN-2005 · Core — Swetha Velamuri (Cisco), Cameron Ferdinands (Groq)