Reposted by Leven Lake
Google met à jour Veo : la génération vidéo gagne en contrôle et en réalisme. moncarnet.com/2025/10/16/g...
October 16, 2025 at 12:45 PM
Google met à jour Veo : la génération vidéo gagne en contrôle et en réalisme. moncarnet.com/2025/10/16/g...
Reposted by Leven Lake
What does Kubernetes 1.34 say about the future of infra?
In The Landscape, Vyom Yadav breaks down upgrades in security, performance, and resource management.
CEL, admission policies, pod identity—it’s all in the details.
thelandsca.pe/2025/10/15/k...
#Kubernetes #CNCF #CloudNative #TheLandscape
In The Landscape, Vyom Yadav breaks down upgrades in security, performance, and resource management.
CEL, admission policies, pod identity—it’s all in the details.
thelandsca.pe/2025/10/15/k...
#Kubernetes #CNCF #CloudNative #TheLandscape
Kubernetes 1.34: Security, Performance, and DRA Go GA - The Landscape
Vyom Yadav, Kubernetes Release Team Lead and Software Engineer at Canonical, joins Sylvain Kalache to discuss what’s new in Kubernetes 1.34. With over 58 enhancements, this release focuses on maturing...
thelandsca.pe
October 16, 2025 at 3:17 PM
What does Kubernetes 1.34 say about the future of infra?
In The Landscape, Vyom Yadav breaks down upgrades in security, performance, and resource management.
CEL, admission policies, pod identity—it’s all in the details.
thelandsca.pe/2025/10/15/k...
#Kubernetes #CNCF #CloudNative #TheLandscape
In The Landscape, Vyom Yadav breaks down upgrades in security, performance, and resource management.
CEL, admission policies, pod identity—it’s all in the details.
thelandsca.pe/2025/10/15/k...
#Kubernetes #CNCF #CloudNative #TheLandscape
Reposted by Leven Lake
OVHcloud met l’IA au service d’un refroidissement écoresponsable dans ses centres de données pour réduire la consommation d’eau de 30 % et celle d’électricité de 50 %. moncarnet.com/2025/10/16/o...
October 16, 2025 at 3:57 PM
OVHcloud met l’IA au service d’un refroidissement écoresponsable dans ses centres de données pour réduire la consommation d’eau de 30 % et celle d’électricité de 50 %. moncarnet.com/2025/10/16/o...
Reposted by Leven Lake
LLMs are monoliths, which can be a major cause for your CPU/GPU compute bills 📈. What if we can build a K8s-native distributed inference stack that brings cache-aware routing and disaggregated serving to LLMs?
Weclome LLM-D which does that, make ur compute bills 📉.
www.youtube.com/shorts/rI8zF...
Weclome LLM-D which does that, make ur compute bills 📉.
www.youtube.com/shorts/rI8zF...
Ep 140 Shorts: Introduction to llm-d Open-source K8s-native Framework for Distributed LLM Inference
YouTube video by Cloud Native Podcast
www.youtube.com
October 15, 2025 at 12:27 PM
LLMs are monoliths, which can be a major cause for your CPU/GPU compute bills 📈. What if we can build a K8s-native distributed inference stack that brings cache-aware routing and disaggregated serving to LLMs?
Weclome LLM-D which does that, make ur compute bills 📉.
www.youtube.com/shorts/rI8zF...
Weclome LLM-D which does that, make ur compute bills 📉.
www.youtube.com/shorts/rI8zF...
Reposted by Leven Lake
llm-d is a new opensource tool and approach designed to make serving generative models on K8s efficient, scalable, and cost-effective by introducing cache-aware routing, disaggregated serving (pre-fill/decode), and K8s-native scheduling & gateways.
🎧 to #CloudNativeFM 👇 youtu.be/2Wtug1kTwUk
🎧 to #CloudNativeFM 👇 youtu.be/2Wtug1kTwUk
Introduction to llm-d Open-source Kubernetes-native Framework for Distributed LLM Inference | Ep 140
YouTube video by Cloud Native Podcast
youtu.be
October 12, 2025 at 4:34 PM
llm-d is a new opensource tool and approach designed to make serving generative models on K8s efficient, scalable, and cost-effective by introducing cache-aware routing, disaggregated serving (pre-fill/decode), and K8s-native scheduling & gateways.
🎧 to #CloudNativeFM 👇 youtu.be/2Wtug1kTwUk
🎧 to #CloudNativeFM 👇 youtu.be/2Wtug1kTwUk
Reposted by Leven Lake
Automatic instrumentation can seem like magic—but it’s not!
The latest #OpenTelemetry blog breaks down how it really works, from monkey patching and bytecode instrumentation to eBPF and runtime APIs.
buff.ly/aWbGOzf
The latest #OpenTelemetry blog breaks down how it really works, from monkey patching and bytecode instrumentation to eBPF and runtime APIs.
buff.ly/aWbGOzf
Demystifying Automatic Instrumentation: How the Magic Actually Works
Despite the rise of OpenTelemetry and eBPF, most developers don’t know what automatic instrumentation actually does under the hood. This post breaks it down—not to suggest you build your own, but to…
opentelemetry.io
October 8, 2025 at 6:41 PM
Automatic instrumentation can seem like magic—but it’s not!
The latest #OpenTelemetry blog breaks down how it really works, from monkey patching and bytecode instrumentation to eBPF and runtime APIs.
buff.ly/aWbGOzf
The latest #OpenTelemetry blog breaks down how it really works, from monkey patching and bytecode instrumentation to eBPF and runtime APIs.
buff.ly/aWbGOzf
Reposted by Leven Lake
Autoscaling vLLM with OpenShift AI | Red Hat Developer developers.redhat.com/articles/202...
Autoscaling vLLM with OpenShift AI | Red Hat Developer
Implement cost-effective LLM serving on OpenShift AI with this step-by-step guide to configuring KServe's Serverless mode for vLLM autoscaling
developers.redhat.com
October 2, 2025 at 10:45 AM
Autoscaling vLLM with OpenShift AI | Red Hat Developer developers.redhat.com/articles/202...
Reposted by Leven Lake
J'ai visionné il y a quelques jours un reportage de la RTS qui traite d'une affaire d'espionnage à l'échelle mondiale qui a concerné une société suisse, leader mondial du chiffrement "Crypto".
Je conseille à tout le monde : youtu.be/Wm1Vk90tUKw?...
Je conseille à tout le monde : youtu.be/Wm1Vk90tUKw?...
Opération Rubicon : espionnage à l'échelle mondiale | RTS
YouTube video by RTS - Radio Télévision Suisse
youtu.be
September 26, 2025 at 7:03 PM
J'ai visionné il y a quelques jours un reportage de la RTS qui traite d'une affaire d'espionnage à l'échelle mondiale qui a concerné une société suisse, leader mondial du chiffrement "Crypto".
Je conseille à tout le monde : youtu.be/Wm1Vk90tUKw?...
Je conseille à tout le monde : youtu.be/Wm1Vk90tUKw?...
Reposted by Leven Lake
What’s new in Flux 2.7 (including the External Artifacts API, Source Composition, Source Watcher), demo gitless GitOps with OCI artifacts, show performance & monitoring tooling, and use the Headlamp plugin to watch reconciliation in real time.
Coming Soon!!!! www.youtube.com/shorts/R86lh...
Coming Soon!!!! www.youtube.com/shorts/R86lh...
September 23, 2025 at 7:25 PM
What’s new in Flux 2.7 (including the External Artifacts API, Source Composition, Source Watcher), demo gitless GitOps with OCI artifacts, show performance & monitoring tooling, and use the Headlamp plugin to watch reconciliation in real time.
Coming Soon!!!! www.youtube.com/shorts/R86lh...
Coming Soon!!!! www.youtube.com/shorts/R86lh...
Reposted by Leven Lake
Kubernetes v1.34: Pods Report DRA Resource Health-
Kubernetes v1.34: Pods Report DRA Resource Health
The rise of AI/ML and other high-performance workloads has made specialized hardware like GPUs, TPUs, and FPGAs a critical component of many Kubernetes clusters. However, as discussed in a previous blog...
kubernetes.io
September 18, 2025 at 6:06 PM
Kubernetes v1.34: Pods Report DRA Resource Health-
Reposted by Leven Lake
Kubernetes v1.34: DRA Consumable Capacity-
Kubernetes v1.34: DRA Consumable Capacity
Dynamic Resource Allocation (DRA) is a Kubernetes API for managing scarce resources across Pods and containers. It enables flexible resource requests, going beyond simply allocating N number of devices...
kubernetes.io
September 18, 2025 at 10:52 PM
Kubernetes v1.34: DRA Consumable Capacity-
Reposted by Leven Lake
Kubernetes v1.34: DRA has graduated to GA-
Kubernetes v1.34: DRA has graduated to GA
Kubernetes 1.34 is here, and it has brought a huge wave of enhancements for Dynamic Resource Allocation (DRA)! This release marks a major milestone with many APIs in the resource.k8s.io group graduating...
kubernetes.io
September 2, 2025 at 6:06 PM
Kubernetes v1.34: DRA has graduated to GA-
Reposted by Leven Lake
Optimize GPU utilization with Kueue and KEDA | Red Hat Developer developers.redhat.com/articles/202...
Optimize GPU utilization with Kueue and KEDA | Red Hat Developer
As GPU demand grows, idle time gets expensive. Learn how to efficiently manage AI workloads on OpenShift AI with Kueue and the custom metrics autoscaler
developers.redhat.com
August 26, 2025 at 1:22 PM
Optimize GPU utilization with Kueue and KEDA | Red Hat Developer developers.redhat.com/articles/202...
Reposted by Leven Lake
Cilium 1.18 release blog is out now. My top two are support for IPv6 kube-proxy replacement and the performance improvements (reduced policy latency 40%, CPU usage down 43% under service churn, and 30% smaller arm64 images)
Cilium 1.18 - Expanded IPv6 Support, Encrypted Overlay, Ingress Bandwidth Controls, Policy Performance Improvements, and More!
isovalent.com
August 11, 2025 at 8:30 AM
Cilium 1.18 release blog is out now. My top two are support for IPv6 kube-proxy replacement and the performance improvements (reduced policy latency 40%, CPU usage down 43% under service churn, and 30% smaller arm64 images)
Reposted by Leven Lake
Let’s shape the future of LLM infrastructure on Kubernetes, together.
👉 Join a SIG. Bring your expertise. Build something that lasts. https://llm-d.ai/docs/community/sigs
👉 Join a SIG. Bring your expertise. Build something that lasts. https://llm-d.ai/docs/community/sigs
July 25, 2025 at 1:54 AM
Let’s shape the future of LLM infrastructure on Kubernetes, together.
👉 Join a SIG. Bring your expertise. Build something that lasts. https://llm-d.ai/docs/community/sigs
👉 Join a SIG. Bring your expertise. Build something that lasts. https://llm-d.ai/docs/community/sigs
Reposted by Leven Lake
🚀 Introducing @kubefloworg.bsky.social Trainer 2.0 — the next evolution in AI model training on @kubernetes.io!
We’re excited to announce 𝗞𝘂𝗯𝗲𝗳𝗹𝗼𝘄 𝗧𝗿𝗮𝗶𝗻𝗲𝗿 2.0 — tailored to simplify and scale AI model training in K8s-native environments.
🔍 What’s New in 2.0?
We’re excited to announce 𝗞𝘂𝗯𝗲𝗳𝗹𝗼𝘄 𝗧𝗿𝗮𝗶𝗻𝗲𝗿 2.0 — tailored to simplify and scale AI model training in K8s-native environments.
🔍 What’s New in 2.0?
July 22, 2025 at 2:37 AM
🚀 Introducing @kubefloworg.bsky.social Trainer 2.0 — the next evolution in AI model training on @kubernetes.io!
We’re excited to announce 𝗞𝘂𝗯𝗲𝗳𝗹𝗼𝘄 𝗧𝗿𝗮𝗶𝗻𝗲𝗿 2.0 — tailored to simplify and scale AI model training in K8s-native environments.
🔍 What’s New in 2.0?
We’re excited to announce 𝗞𝘂𝗯𝗲𝗳𝗹𝗼𝘄 𝗧𝗿𝗮𝗶𝗻𝗲𝗿 2.0 — tailored to simplify and scale AI model training in K8s-native environments.
🔍 What’s New in 2.0?
Reposted by Leven Lake
Learn how to build a flexible GenAI platform using the open-source solutions Envoy AI Gateway, KServe, & complementary tools
- Self-Hosted Model Serving w/KServe
- Observability, Control, and Optimization for Prod Readiness
- Policy Enforcement and Guardrails
aigateway.envoyproxy.io/blog/envoy-a...
- Self-Hosted Model Serving w/KServe
- Observability, Control, and Optimization for Prod Readiness
- Policy Enforcement and Guardrails
aigateway.envoyproxy.io/blog/envoy-a...
July 17, 2025 at 5:20 PM
Learn how to build a flexible GenAI platform using the open-source solutions Envoy AI Gateway, KServe, & complementary tools
- Self-Hosted Model Serving w/KServe
- Observability, Control, and Optimization for Prod Readiness
- Policy Enforcement and Guardrails
aigateway.envoyproxy.io/blog/envoy-a...
- Self-Hosted Model Serving w/KServe
- Observability, Control, and Optimization for Prod Readiness
- Policy Enforcement and Guardrails
aigateway.envoyproxy.io/blog/envoy-a...
Reposted by Leven Lake
Introducing Gateway API Inference Extension-
Introducing Gateway API Inference Extension
Modern generative AI and large language model (LLM) services create unique traffic-routing challenges on Kubernetes. Unlike typical short-lived, stateless web requests, LLM inference sessions are often...
kubernetes.io
June 5, 2025 at 7:52 PM
Introducing Gateway API Inference Extension-
Reposted by Leven Lake
Kubernetes doesn’t make egress easy, scattering it across NAT tables, host routing rules, and CNI quirks. Teams end up reaching for hacky solutions like standalone proxies, policy engines, even hand-configured nodes
Enter stand Alone Egress Gateway
isovalent.com/blog/post/is...
Enter stand Alone Egress Gateway
isovalent.com/blog/post/is...
June 4, 2025 at 8:30 AM
Kubernetes doesn’t make egress easy, scattering it across NAT tables, host routing rules, and CNI quirks. Teams end up reaching for hacky solutions like standalone proxies, policy engines, even hand-configured nodes
Enter stand Alone Egress Gateway
isovalent.com/blog/post/is...
Enter stand Alone Egress Gateway
isovalent.com/blog/post/is...
Reposted by Leven Lake
We are excited to announce KServe v0.15 release, marking a significant leap forward in serving both predictive and generative AI models.
GenAI features: Envoy AI Gateway integration, multi-node inference via vLLM, LLM autoscaler, distributed KV cache via LMCache.
kserve.github.io/website/mast...
GenAI features: Envoy AI Gateway integration, multi-node inference via vLLM, LLM autoscaler, distributed KV cache via LMCache.
kserve.github.io/website/mast...
KServe 0.15 Release - KServe Documentation Website
KServe Documentation
kserve.github.io
May 29, 2025 at 2:44 PM
We are excited to announce KServe v0.15 release, marking a significant leap forward in serving both predictive and generative AI models.
GenAI features: Envoy AI Gateway integration, multi-node inference via vLLM, LLM autoscaler, distributed KV cache via LMCache.
kserve.github.io/website/mast...
GenAI features: Envoy AI Gateway integration, multi-node inference via vLLM, LLM autoscaler, distributed KV cache via LMCache.
kserve.github.io/website/mast...
Reposted by Leven Lake
ML Engineers often struggle with inconsistent packaging mechanisms, forcing them to repackage models multiple times, slowing down development and increasing risk.
@Kit_Ops is solving these issues by standardizing model packaging & deployment.
🎧 to know more #cloudnativefm -> youtu.be/BM9PcoK2Ik8
@Kit_Ops is solving these issues by standardizing model packaging & deployment.
🎧 to know more #cloudnativefm -> youtu.be/BM9PcoK2Ik8
May 26, 2025 at 6:12 PM
ML Engineers often struggle with inconsistent packaging mechanisms, forcing them to repackage models multiple times, slowing down development and increasing risk.
@Kit_Ops is solving these issues by standardizing model packaging & deployment.
🎧 to know more #cloudnativefm -> youtu.be/BM9PcoK2Ik8
@Kit_Ops is solving these issues by standardizing model packaging & deployment.
🎧 to know more #cloudnativefm -> youtu.be/BM9PcoK2Ik8
Reposted by Leven Lake
Reposted by Leven Lake
Kubernetes v1.33: New features in DRA-
Kubernetes v1.33: New features in DRA
Kubernetes Dynamic Resource Allocation (DRA) was originally introduced as an alpha feature in the v1.26 release, and then went through a significant redesign for Kubernetes v1.31. The main DRA feature...
kubernetes.io
May 2, 2025 at 3:06 PM
Kubernetes v1.33: New features in DRA-
Reposted by Leven Lake
Kubernetes v1.33: HorizontalPodAutoscaler Configurable Tolerance-
Kubernetes v1.33: HorizontalPodAutoscaler Configurable Tolerance
This post describes configurable tolerance for horizontal Pod autoscaling, a new alpha feature first available in Kubernetes 1.33. What is it? Horizontal Pod Autoscaling is a well-known Kubernetes feature...
kubernetes.io
April 29, 2025 at 3:09 PM
Kubernetes v1.33: HorizontalPodAutoscaler Configurable Tolerance-
Reposted by Leven Lake
Un bel exemple d’ingéniosité : ce dispositif anti-moustiques combine une moustiquaire avec un ventilateur, sur lequel une lampe UV a été fixée à l’arrière. Attirés par la lumière, les moustiques volent vers elle et sont ensuite aspirés dans un sac.
April 23, 2025 at 4:59 PM
Un bel exemple d’ingéniosité : ce dispositif anti-moustiques combine une moustiquaire avec un ventilateur, sur lequel une lampe UV a été fixée à l’arrière. Attirés par la lumière, les moustiques volent vers elle et sont ensuite aspirés dans un sac.