What’s Cooking

NVIDIABlog10 Jul

Reducing High-Bandwidth Memory Bottlenecks in JAX-Based LLM Training with Host Offloading

CohereBlog10 Jul

Hardware-Aware, Dynamic Speculative Decoding (DSD)

NVIDIABlog10 Jul

Kernel Fusion in NVIDIA CUDA: Optimizing Memory Traffic and Launch Overhead

NVIDIABlog10 Jul

AI Model Co-Design: Hardware-Friendly LLM Design

GitHubBlog10 Jul

Better tools made Copilot code review worse. Here's how we actually improved it.

MicrosoftBlog10 Jul

Shrinking Azure Pipeline task extensions using esbuild

DataRobotBlog10 Jul

Your agents are using your credentials, and that is the problem

NVIDIABlog10 Jul

Accelerating End-to-End Co-Folding Performance with NVIDIA BioNeMo Agent Toolkit

CloudflareBlog10 Jul

Improving Smart Tiered Cache for Public Cloud Regions

RedisBlog10 Jul

Best databases for AI agent memory: a 2026 comparison

GrabBlog10 Jul

Agent platform (Part 1): How we help Grab build and run AI agents at scale

LyftBlog10 Jul

From Day 1 to Production: Building Lyft’s Analytics & Rides Intelligence Assistant as Onboarding…

ConfluentBlog10 Jul

Tableflow: Turn Kafka Topics into Iceberg Tables

Fireworks AIBlog10 Jul

Optimizing MiniMax M3 Sparse Attention on NVIDIA Blackwell

DecagonBlog9 Jul

What an air-gapped AI deployment actually requires

NVIDIABlog9 Jul

Synthetic Data Generation for Financial AI Research with NVIDIA NeMo

You’re caught up

That’s every post that day.