v0.34.3-rc1
server: allow registry cross-host redirects among allowlisted hosts (…
DC AI 热点
全部 AI 动态
9月19日2026-09-19
v0.30.0rc2
[Bugfix][NIXL] Avoid receive reports for notification-only requests (…
Digitalization is helping universities do more with less. Swansea University shows us how.
UK universities released 1.4 million tonnes of carbon dioxide last year, and the sector faces an estimated £37 billion bill to reach net zero—a bill that lands on institutions already stretched by tight budgets and rising costs. For most, decarbonizing isn’t a resourcing problem so... The post Digitalization is helping universities do more with less. Swansea University shows us how. appeared first on Schneider Electric Blog .
Amazon SageMaker Inference: 2026 year-to-date launches in review
Amazon SageMaker AI shipped 13 inference launches in year-to-date across two deployment paths: fully managed endpoints and Amazon SageMaker HyperPod Inference. This post reviews each launch, from inference recommendations and capacity-aware instance pools to tiered KV caching and disaggregated prefill and decode.
Introducing Kimi K3 on Amazon Bedrock
Kimi K3 from Moonshot AI is now available on Amazon Bedrock, giving you a powerful new open-weight option for coding and knowledge work. It offers native vision, a 1-million-token context window, and explicit prompt caching to reduce latency and input costs.
From pilot to production: Why enterprise AI needs an infrastructure strategy
For the past two years, enterprise AI has felt promising, but ethereal: thrilling to watch from a distance, but not something most companies could grasp themselves. We’ve all seen the demos, read the headlines, and over one billion of us now use standalone AI tools... The post From pilot to production: Why enterprise AI needs an infrastructure strategy appeared first on Schneider Electric Blog .
9月18日2026-09-18
How CSIRO built scalable, cost-optimized genomic variant querying on AWS
Learn how researchers at CSIRO, Australia's national science agency, built Serverless Beacon (sBeacon), a scalable serverless solution for securely querying genomic variant data on AWS. sBeacon implements the GA4GH Beacon standard using Amazon S3, AWS Lambda, Amazon DynamoDB, and Amazon Athena to support production-scale clinical and research applications.
AI in logistics: from visibility to orchestration
For years, logistics transformation has been built around visibility. Organizations invested heavily in dashboards, control towers, tracking platforms, and analytics to understand increasingly complex supply chains. Visibility remains essential, but it is no longer the end goal. The real question is what organizations do with... The post AI in logistics: from visibility to orchestration appeared first on Schneider Electric Blog .
How Equinix cut operational overhead with a shared services architecture on Amazon EKS
Equinix, the world's digital infrastructure company, built a shared services architecture on Amazon EKS to eliminate the operational sprawl of its self-managed Kubernetes environment. Learn how a multi-account North Star architecture centralized governance and shared services, delivering 4x faster deployments and 40% less operational overhead.
v0.34.2-rc2: mlxrunner: Release freed KV buffers during speculative decode
The decode loop releases MLX's pool of freed buffers every 256 generated tokens, which is also how often the KV cache grows and drops its previous, smaller buffers. The check fires only when the token count lands exactly on a multiple of 256. Speculative decoding emits several tokens per round, so most rounds step over the boundary and the pool is never released. Each growth at a long context leaves several GB of buffers that no later allocation can reuse, so the runner's footprint keeps climbing over a long generation until the system runs out of memory. We now release the pool whenever a round crosses a multiple of 256 tokens, which is what
Scaling Multi-GPU Video Captioning with PyNvVideoCodec and vLLM
How to leverage NVIDIA Hardware Video Decoders to Achieve Multi-GPU Scaling in Video Captioning and Description tasks.
9月17日2026-09-17
Building cloud-native PACS on AWS
A hybrid cloud architecture pattern for modernizing medical imaging on AWS. Learn how multi-hospital networks can centralize PACS archives, enable cross-facility interoperability, and use Amazon S3 storage tiers to manage cost and retention at scale.
How DHI Group accelerates generative AI workloads from idea to production using hackathons
Learn how DHI Group partnered with AWS to move generative AI workloads from idea to production using a structured hackathon. This post covers the Hackathon Acceleration Package, the winning ClearanceJobs and AgileATS agentic architecture on Amazon Bedrock AgentCore, and the principles that make hackathons a repeatable path to production.
What a 190% ROI on Network Modernization Looks Like
Enterprises are moving more data between more distributed endpoints, in more places, than ever before—which makes network modernization essential. Yet many leaders struggle to…
v0.30.0rc1: [Bugfix] Isolate supplemental FlashInfer BF16 autotuning (#57285)
Signed-off-by: jiahanc 173873397+jiahanc@users.noreply.github.com Co-authored-by: OpenAI Codex codex@openai.com
Zombie Workloads Haunt Data Center Efficiency Efforts
Abandoned jobs, instances, and volumes can run indefinitely. FinOps tools help, but GPU-era AI demands new zombie-hunting methods.
Helping bring the world’s first large-scale, near-zero emissions steel plant online
Video opens with archival footage of smoky, coal-fired steel factories, then transitions to clean, modern exterior shots of Stegra's new facility and a clear digital animation showing how green hydrogen replaces coal to produce near-zero emission steel.
proto-v0.3.0
Release vllm-proto 0.3.0
v0.34.2-rc1: mlxrunner: lay out model by contract, checkpoint and construction
model is one package with three jobs: the contract between the runner and the architectures, the opened checkpoint, and building nn layers from checkpoint tensors. Its files did not say which was which. base.go carried the folded package's name over the interfaces and the registry, root.go held the safetensors header scan next to Root, and quant.go mixed the nvfp4 global-scale helpers with quant parameter resolution. base.go becomes model.go, named for what it holds. root.go keeps Root and Open; TensorQuantInfo and the header scan join quant.go, so everything the checkpoint says about quantization is read and resolved in one file. The global-
Translating CUDA Tile Operations from Python to Rust Using Agentic AI
cuTile Rust (cutile-rs) is a tile-based system for safe, idiomatic GPU kernel authoring in the Rust programming language. Extending the Rust ownership model to...
9月16日2026-09-16
NVIDIA Vera Rubin NVL72 Delivers Leading Performance in MLPerf Inference v6.1 Debut
System performance, efficient infrastructure scaling and continuous software optimization are key levers that determine AI inference economics. Higher system performance means more tokens generated, resulting in higher revenue. Efficient scaling means throughput grows proportionally as hardware gets added, requiring fewer resources to serve users at scale. Continuous optimization means generating more value from infrastructure investments. […]
Emerald AI, Google and NVIDIA Launch Alliance to Advance Flexible AI Data Centers
AI factories are the infrastructure of the intelligence era. Scaling them responsibly will depend as much on innovation across the grid as inside the data center. Today, Emerald AI, Google and NVIDIA announced the launch of the AI Energy Management Alliance (AEMA), a first-of-its-kind coalition advancing data centers that can dynamically manage their electricity use […]
Building the materials foundation for AI
The AI boom is becoming a materials challenge. As AI pushes computing into new territory, the materials behind that infrastructure are becoming just as crucial as the algorithms running on it. Semiconductors and data centers are approaching physical limits around performance, thermal management, electrical efficiency, and reliability, creating new demands for materials that can do…
Why Public Internet Routing Is Breaking Enterprise AI Performance
AI success isn’t just about hardware and models. Where organizations host workloads matters, as does the connectivity across those distributed workloads. When enterprises place…
proto-v0.2.0: vllm-proto 0.2.0
Validated by PR #56538 CI at fa2a26f .
EcoStruxure™ ArcFM: Turning geospatial intelligence into operational reality for modern gas utilities
As regulatory requirements continue to evolve, gas distribution operators face growing pressure to demonstrate network safety and reliability. They must also show strong environmental performance across their operations. Requirements include Distribution Integrity Management Program (DIMP) compliance and pipeline replacement initiatives. Utilities are also working to... The post EcoStruxure™ ArcFM: Turning geospatial intelligence into operational reality for modern gas utilities appeared first on Schneider Electric Blog .
How state policies change cooling decisions across India’s data centre hubs
Author: Sumati Sahgal, VP, Data Centre & Secure Power A data centre operator planning capacity in Mumbai cannot assume the same cooling economics will apply in Chennai, Hyderabad, Bengaluru, or Noida. India’s data centre incentives are largely set at the state level, where electricity concessions... The post How state policies change cooling decisions across India’s data centre hubs appeared first on Schneider Electric Blog .
Kubernetes v1.37: Pod-Level Resource Managers graduated to Beta
With the release of Kubernetes v1.37, the Pod-Level Resource Managers feature has graduated to Beta status (disabled by default)! First introduced as an Alpha feature in Kubernetes v1.36 , this enhancement builds on Pod-Level Resources by equipping Kubelet's Topology Manager, CPU Manager, and Memory Manager to use Pod-level resource declarations ( .spec.resources ) directly when making hardware placement decisions. Bringing pod-level resources to node managers Before this feature, obtaining exclusive NUMA-aligned CPU cores or memory for latency-critical applications forced cluster operators into an all-or-nothing choice: assign integer resour
From Megawatts to Tokens: How NVIDIA Maximizes AI Factory Production
On a sweltering August evening in Silicon Valley, as the sun dropped and air conditioning loads spiked, Silicon Valley Power sent a signal to an AI factory to adjust its power consumption. Varun Sivaram was watching on Zoom with about forty others — his team at Emerald AI in their San Francisco conference room, engineers […]
AI Infra Summit: NVIDIA Vera Rubin and DSX Platform Advancements Showcase Energy Efficiencies of Optimizing Tokens Per Watt for AI Factories
Ian Buck, vice president of hyperscale and high-performance computing at NVIDIA, Tuesday spoke on AI factory efficiency at the AI Infra Summit, the Santa Clara Convention Center event that has morphed into a Coachella of infrastructure tech. Before a packed audience — with more than 8,000 attendees this year, up from 3,500 last year — […]