Azure Kubernetes Service
PulseAugur coverage of Azure Kubernetes Service — every cluster mentioning Azure Kubernetes Service across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
NVIDIA open-sources OSMO for unified AI robotics development
NVIDIA has open-sourced OSMO, a Kubernetes-native workflow orchestrator designed to streamline AI development for robotics. OSMO allows developers to define training, simulation, and robot testing pipelines in a single …
-
Anyscale's Azure Kubernetes Architecture Explained
This article provides a detailed technical explanation of Anyscale's architecture on Azure Kubernetes Service (AKS). It outlines the two-plane Azure setup and describes the Ray Data, Train, and Serve pipeline. The piece…
-
Secure MLOps Environment Setup with Azure ML
This article details how to establish a secure MLOps environment using Azure ML infrastructure. It focuses on setting up robust security measures for researchers, covering aspects from development to deployment. The gui…
-
GPU sizing guide for AI models focuses on VRAM for weights and KV cache
This article provides a method for Site Reliability Engineers to estimate the GPU memory (VRAM) required for hosting AI models. It breaks down VRAM consumption into model weights, the KV cache for concurrent requests, a…
-
vLLM autoscaling flapping fixed by choosing better signals
This article addresses the issue of "flapping" in vLLM autoscalers, where pods rapidly cycle between running and failing states, leading to increased costs and latency. The author explains that this problem often stems …
-
New frameworks boost AI long video understanding efficiency
Researchers have developed two new frameworks, EcoFrame and EviSelect, designed to improve the efficiency of long video understanding by large language models. EcoFrame uses a training-free approach that adapts the fram…
-
Self-Hosting Ollama Llama 3.2 Model in AKS for Log Analysis
This article details the process of self-hosting the Ollama Llama 3.2–1b model within an Azure Kubernetes Service (AKS) cluster. The primary goal is to enable log analysis capabilities by deploying the model in a contro…
-
Anyscale AI platform enters public preview on Azure
Anyscale has launched a public preview of its AI compute platform integrated directly into Microsoft Azure. This integration allows enterprises to deploy and manage AI workloads, including distributed training and large…
-
CREST method efficiently selects key frames from long videos
Researchers have developed CREST, a novel method for efficiently selecting key frames from long videos. This training-free approach leverages the temporal geometry of query-frame relevance, specifically focusing on loca…
-
Anyscale launches managed AI service on Azure for Ray workloads
Anyscale has launched a private preview of its managed service on Microsoft Azure, designed to help enterprises build and scale AI workloads. This integration allows users to provision and manage Anyscale, which is powe…
-
A2A agents hit Azure production snags due to Nginx SSE buffering
The author details the challenges encountered when deploying their A2A agent protocol to Azure, specifically highlighting issues with server-sent events (SSE) buffering on the Nginx ingress controller. This single annot…
-
GitHub Actions, GHCR, and Azure streamline private AKS container deployment
This article details a technical process for deploying a containerized application to a private Azure Kubernetes Service (AKS) cluster. It outlines the use of GitHub Actions for continuous integration and continuous dep…
-
Microsoft enhances Azure Local for large-scale sovereign cloud deployments
Microsoft has significantly upgraded Azure Local, its on-premises cloud offering, to support large-scale sovereign cloud deployments. The enhancements include independent scaling of compute and storage, the ability to u…