Register and share your invite link to earn from video plays and referrals.

Search results for Kubernetes-native
Kubernetes-native community
One keyword maps to one global community path.
Create community
People
Not Found
Tweets including Kubernetes-native
Convert #OpenShift# BuildConfigs to #Kubernetes-native# builds with crane-plugin-buildconfig-to-builds. Handle Git sources, environment variables, and build strategies while reading warnings before applying them to your target cluster.
Show more
Official Helm charts for the Boundary controller and worker are now available, bringing Kubernetes-native deployment to both self-managed and HCP Boundary environments. Read more ➡️
Show more
💾 TL;DR: reuse a KV cache computed on another node's GPU straight through CXL memory, up to 36.6x faster. Seagate proposes a Kubernetes-native way to share CXL memory across the cluster. Title: Composable CXL Memory as a Kubernetes-Native Shared Memory for LLM Serving URL: 📌 Highlights 🧩 A Kubernetes DRA driver turns CXL regions into schedulable cluster resources 🗂 No Redis/etcd needed, KV slots are tracked inside the region itself 🚀 Cross-node reuse hits 36.6x speedup over recompute at 32K-token prefixes 🎯 Hit rates reach 95.4-99.5% ⚖️ Cross-node vs same-node latency differs by only 1-4% 🐢 Still 1.15-1.70x slower than an on-GPU VRAM prefix cache hit 🔧 Measured 5.8 GB/s out of a 27 GB/s fabric ceiling, room to grow with zero-copy DMA For serving that needs to reuse long prefixes across GPU nodes, this feels like a genuinely practical option. #LLMInference# #Kubernetes#
Show more
We've published a guide to building an open AI-native stack on Kubernetes for #KubeCon# #CloudNativeCon#. Scale from prototype wrappers to multi-host model serving, dynamic GPU/TPU allocation, and production agent orchestration ↓
Show more
41.8 GB/sec. 133.5 million rows/sec. One native Snowflake table. Our synthetic Snowpipe Streaming benchmark in AWS us-west-2 sustained 41.8 GB/sec of uncompressed throughput with Elastic Channels. Throughput grew linearly as we scaled from 15 to 455 Kubernetes workers. The setup combined Elastic Channels, 1-vCPU worker pods and Rust-based encoding to reduce client-side overhead. Building telemetry or log pipelines? See the benchmark method, latency measurements and how to start with one worker:
Show more
It's true we no longer need to keep our laptops open, but for all the recent progress of OpenAI and Anthropic, cloud-based agent harnesses aren't fully solved yet. Maybe we need the creators of Kubernetes to tackle the problem? Stacklok is built by two of them, @cmcluck & @jbeda, and they aim to bring agent harnesses fully to the cloud. We talk to McLuckie and Beda about their "cloud-native harness":
Show more
Jensen Huang: America Needs Open Source to Win AI... Because Open Source Lets Every American Win @JensenHuang: “In the last six months, $400B of venture funding went into AI-native companies. 80% of them use open models. If not for open models, how could they build their dream? Because their dream could be different. Obviously, it'll be different than the frontier labs' dreams. America has so many different ways to innovate. That's one of our core strengths. Great ideas just coming out of the fountain, and so open models enables that.” @friedberg: “Does it matter if the open models come from China or the US?” Jensen: “Probably the vast majority of the world's contribution to open source today is coming from China. They just have a lot more engineers. They contribute to open source today. We download Linux, we download Kubernetes, we download all the software. A lot of it has been touched by (the) Chinese, and once you download it, it's yours. We fork it, we improve it, we make it ours. And so when you download one of these Chinese models, it just happens to be made by some really great researchers in China, but it's now yours. If we want to win the AI race, it's not about a few technology companies winning the AI race. It's about every company in America, every industry, every researcher, every teacher, every student, every startup, everybody wins. Some of them will use closed models. A lot of them will use open models.” $NVDA ------------------------------ Thanks to our partners for making this possible! Google for Startups connects founders with the right people, products, and best practices to help startups build faster and go further. Explore ideas, industries, and technologies worth understanding with Chamath every week on Learn with Me:
Show more
3D Kubernetes simulation playable in the browser
Getting AI running on Kubernetes is only the beginning. Securing it for production means protecting the infrastructure underneath it. See how Vault brings secrets, certificates, and encryption controls into Kubernetes workflows.
Show more
Optimize your #Kubernetes# fleet with right-sizing recommendations in #RedHat# Advanced Cluster Management 5️⃣. Balance application performance and infrastructure costs using configurable percentile profiles for CPU and memory across namespaces and VMs.
Show more