Aug 06, 2026

The State of Model Routing — NVIDIA, Cognition, OpenRouter

A deep dive into model routing strategies for AI/ML production, featuring experts from Cognition, OpenRouter, and NVIDIA. Key topics include optimizing costs with multi-model systems, delegating tasks between frontier and smaller models, managing context efficiently (sidekicks, compaction), and adapting to dynamic task complexities. The panel discusses the fragility of naive routing, the cost implications of in-distribution vs. out-of-distribution tasks, and the evolution of auto-routers driven by real-world usage patterns like OpenClaw's heartbeats. Insights also cover NVIDIA's Flex Run for dynamic model sizing, hallucination probes for detecting model limitations, and the future of hybrid local/cloud routing and model collaboration.

Jul 31, 2026

Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It — Olive Song

Olive Song, RL lead at MiniMax, details the engineering behind MiniMax's open-weight models, focusing on M3's multimodal and agentic capabilities, the necessity of day-zero inference stack readiness, and continuous GPU kernel optimization. She discusses multimodal training challenges, long-horizon task evaluation, and expresses optimism for open models rapidly closing the gap with frontier labs.

Jun 30, 2026

How KV Cache Speeds Up LLMs for Faster AI Models on GPUs

LLMs often slow down under heavy traffic due to inefficient GPU memory management during inference. This overview explains how KV cache and Paged Attention, implemented in VLLM, optimize memory usage across prefill and decode phases, significantly boosting LLM throughput, reducing latency, and improving GPU utilization through advanced context handling and specific tuning techniques like prefix caching and speculative decoding.

Jun 28, 2026

Turbocharge Your Agent's Retrieval with TurboQuant - Shashi Jagtap, Superagentic AI

This talk introduces TurboQuant, a training-free compression method from Google Research that reduces embedding memory footprint by 5x (from 32-bit to 3-4 bits) without losing search quality. It details how TurboQuant works through scalar quantization and a crucial one-bit error correction step, QJL, enabling agents to remember more on existing hardware by optimizing both KV cache and RAG vector stores. A live demo showcases its effectiveness, making it a vendor-neutral solution for efficient AI agent retrieval.

May 21, 2026

CAG vs Long Context: How AI Models Use and Remember Information

Martin Keen explains how Long Context and Cache Augmented Generation (CAG) serve as powerful alternatives to RAG for providing external knowledge to LLMs. This summary details the mechanics of each approach, the role of the KV cache, the practical application through prompt caching, and the trade-offs in performance, cost, and latency for real-world AI workloads.