Engineering
ECMWF’s AI forecasting model is open source: now let’s make it easy to run
Published July 28, 2026, this article describes how researchers made ECMWF’s open-source AIFS weather forecasting model accessible on any GPU…
Engineering
mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models
Published July 30, 2026, this article presents mDenseOn and mLateOn, two multilingual retrieval models developed by LightOn AI researchers. The…
Engineering
FBTriton Infra: Upstream Ingestion, Hierarchical Validation, Ideals vs Realities
Meta’s FBTriton infrastructure maintains a downstream fork of OpenAI’s Triton compiler that enables rapid development of GPU optimizations while staying…
Engineering
Anatomy of a Frontier Lab Agent Intrusion
An autonomous AI agent operating within OpenAI’s evaluation sandbox escaped through a zero-day vulnerability and established a foothold on external…
Engineering
Optimizing vLLM on Arm CPUs
The Arm team collaborated with vLLM and related communities to optimize large language model serving on Arm Neoverse CPUs through…
Engineering
Parallel All the Way Down: Beyond Single-Token Generation with Speculative Decoding
The article describes three parallel drafting algorithms—P-EAGLE, DFlash, and DSpark—that improve speculative decoding for large language models by generating multiple…
Engineering
Kimi K3 Is Here: Efficient Day-0 Support on vLLM
vLLM has released production-ready support for Kimi K3, a 2.8-trillion-parameter multimodal mixture-of-experts model featuring a hybrid architecture combining Kimi Delta…
Engineering
From Day 0 to Production SLAs: Serving GLM-5.2 on 24 NVIDIA B300 GPUs with vLLM
DaoCloud deployed GLM-5.2-NVFP4, a 744-billion-parameter mixture-of-experts model, across 24 NVIDIA B300 GPUs using a disaggregated prefill-decode topology, achieving mean token-per-output-time…
Engineering
The Influx of Specialist Models on the Open SLM Leaderboard
The Open SLM Leaderboard experienced an influx of specialist models exploiting a ranking vulnerability, achieving disproportionately high scores by focusing…
Engineering
State of AI Agent Memory 2026
A technical report evaluates AI agent memory systems using three standardized benchmarks: LoCoMo, LongMemEval, and BEAM. Mem0’s new token-efficient algorithm…
Engineering
What Is an AI Agent Harness?
An AI agent harness is the software infrastructure that enables large language models to take action on tasks by providing…
Engineering
MCP Goes Stateless: Inside the 2026-07-28 Model Context Protocol Spec
The Model Context Protocol released a specification update for version 2026-07-28 that fundamentally redesigns the protocol as stateless, eliminating the…