←
Modelplane19 posts
Modelplane avatar

Modelplane

@ModelplaneAI

The open source control plane for AI inference

◷ Joined June 2026▧ 12 Photos and videos
Bassam Tabbara avatar
⟳ Modelplane retweeted
Bassam Tabbara@bassamtabbara·Nov 12

Great conversation with @theCUBE at @KubeCon_ about the future of AI infrastructure. Inference is moving beyond individual clusters and clouds. The next generation of control planes needs to be built in the open, not behind closed doors. We talked @ModelplaneAI and what’s ahead. youtu.be/0QHmMCdppNQ

Modelplane avatar
Modelplane@ModelplaneAI·Nov 11

✈️ Big milestone for Modelplane! Today, Upbound submitted Modelplane for CNCF Sandbox consideration. Six releases, new integrations and community contributions in five months. We're building an open control plane for fleet-wide AI inference. modelplane.ai/blog/five-mont…

Post attachment
Modelplane avatar
Modelplane@ModelplaneAI·Nov 3

Getting a model running is the easy part. 📈 Practitioners go live at Inference Day on operating inference in the real world, from observability and cost to what enterprise teams face every day. November 5, 10:00 AM PT Register here 👉 modelplane.ai/inference-day

Post attachment
Modelplane avatar
Modelplane@ModelplaneAI·Nov 2

Running inference at scale starts with the platform underneath. 🏗️ Building the Platform for AI: maintainers and contributors from Kubernetes, Metal3, Crossplane and Modelplane go live at Inference Day, from the cloud to bare metal. modelplane.ai/inference-day

Post attachment
Modelplane avatar
Modelplane@ModelplaneAI·Oct 29

How do you serve models fast, reliably, and at scale? ⚡ Maintainers behind NVIDIA Dynamo, KServe, Agent Router and Modelplane break it down live at Inference Day, from routing requests to running the engine. November 5, 9:00 AM PT. Free. 👉 modelplane.ai/inference-day

Post attachment
Modelplane avatar
Modelplane@ModelplaneAI·Oct 27

New to the AI inference stack? Start here. 🛠️ @vfarcic closes Inference Day with Inference 101, a practical look at the emerging inference stack and what platform engineers need to know. Nov 5, 10:30 AM PT / 7:30 PM CET. Free. Register here 👉 modelplane.ai/inference-day

Post attachment
Bassam Tabbara avatar
⟳ Modelplane retweeted
Bassam Tabbara@bassamtabbara·Sep 11

Big release today with integration with @NVIDIAAI . We’ve been working with Nvidia on this and excited to release the work. A powerful story - NVIDIA Dynamo runs inference on the cluster, AICR ensures it’s well matched to the hardware, and Modelplane turns into a global inference service.

The stack is a per-cluster choice in @Modelplane v0.4, and it's immutable, so adoption is incremental. Stand up a @NVIDIA Dynamo cluster next to the ones you already run. Same ModelDeployment on both. Blog link: modelplane.ai/blog/modelplan…

Post attachment
Modelplane avatar
Modelplane@ModelplaneAI·Aug 27

Compute isn't the bottleneck. The missing control loop is. @CoreWeave runs @kubernetesio all the way down. No VMs, just containers and a reconcile loop. That's not a coincidence, it's the only pattern that survives at AI scale. @bassamtabbara explains on Hello, Agent! 👇🎧

The largest inference operations share one pattern: a declarative reconcile loop. @bassamtabbara, Founder and CEO at @upbound_io, points to CoreWeave, running Kubernetes to no VMs, just containers. Click here for the "Hello, Agent!" episode. bit.ly/4gUOAv6 #RealTimeData #DataStreaming #Redpanda

Post attachment
Modelplane avatar
Modelplane@ModelplaneAI·Aug 13

Modelplane v0.3 is out. Run Claude Code on your own GPUs: we now serve the Anthropic Messages API end to end. Plus @Vultr as a fifth cluster provider, per-cluster credentials for multi-account fleets, and a local test that runs with no cloud and no GPU. → modelplane.ai/blog/modelplan…

Post attachment
Modelplane avatar
Modelplane@ModelplaneAI·Aug 12

"Day 0 support" usually means someone dropped everything. Nemotron 3.5 Lightning was serving on Modelplane the same afternoon @nvidia shipped it and nothing in Modelplane changed. We don't wrap engines or pin versions. modelplane.ai/blog/nemotron-… #vLLM

Modelplane avatar
Modelplane@ModelplaneAI·Jul 23

We measured our Claude Code usage at API prices: 13x our seat cost on average, 52x for our heaviest engineer. Nothing broke. That's Claude Code working as intended, once you see the meter. What's your subsidy multiple? → modelplane.ai/blog/ai-coding…

Post attachment
Modelplane avatar
Modelplane@ModelplaneAI·Jul 20

Cluster-level inference tooling is fine. It just doesn't help you orchestrate the GPUs you own. Nobody at scale runs one cluster. The fix: treat the ones you own as one pool. That's the fleet-level API we designed. How we built it →modelplane.ai/blog/how-we-de…

Post attachment