Accelerating Mamba-2 with High-Performance Forward Pass Kernels in NVIDIA CUDA Tile
Engineering
Engineering News
Tooling, infrastructure and hands-on machine learning
Pegasus 1.5 from TwelveLabs is now available in Amazon Bedrock
Engineering
How Deepgram optimized voice AI at scale with AWS Trainium
Engineering
Push-based KV transfer to improve TTFT and TPOT for disaggregated inference in vLLM
Engineering
Improve TTFT for multi-turn agentic workloads with bi-directional KV transfer in vLLM
Engineering
Claude Haiku 5.5: What’s New and How to Use It for Fast, Cheap AI Workflows
Engineering
LangChain vs. LlamaIndex vs. Building From Scratch: Here’s What I Suggest
Engineering
MiniMax Just Launched M3.1 Flash: 428B MoE Agentic Model at $0.15/M Input
Engineering
7 Checks to Run Before Trusting AI-Generated Code
Engineering
NVIDIA Open Sources Run:ai Under Apache 2.0 for Kubernetes GPU Orchestration
Engineering
Mistral AI Releases Timestral: A 209M Forecasting Model Family That Outperforms Google’s TimesFM-3
Engineering
TinyFish Makes Search Free: What It Really Costs an AI Agent to Read the Web
Engineering