Microsoft makes Foundry Managed Compute generally available for open models
Tech

Microsoft makes Foundry Managed Compute generally available for open models

TechNews Editorial
TechNews EditorialNov 20, 2026 · 1 min read
Share

Why it matters

Foundry users can deploy open models without operating the GPUs or serving software themselves, according to Microsoft.

The facts

  • Microsoft says Foundry Managed Compute is generally available for serving open models on dedicated GPUs.
  • The service offers more than 150 open models, with NVIDIA and AMD GPU options depending on the model.
  • LoRA adapter deployment is in preview, and Bring Your Own Weights is in limited public preview.

Advertisement

Microsoft says Foundry Managed Compute is generally available for serving open models on dedicated GPUs. The company provisions the GPUs, maintains the containers and operates the serving software for deployments made through Foundry.

The service launched in public preview in June 2026. Microsoft says its catalog now offers more than 150 open models for Managed Compute, including recent additions for reasoning, coding, search, document processing and speech.

Teams choose a model and a deployment template that sets its context length, serving software and GPU configuration. Depending on the model, they can use NVIDIA A100, H100 or H200 GPUs, or AMD MI300X GPUs. Microsoft has also added deployment options in United States and European Union Data Zones. The deployment wizard shows the hourly cost before launch.

Teams can add instances behind an existing endpoint as traffic grows. Each instance uses the number of GPUs in its template. Microsoft says a DeepSeek V4.1 Flash (1017) deployment using four MI300X GPUs per instance would grow from four to 20 GPUs when scaled from one instance to five. Customers pay hourly for each accelerator.

Five accelerator boards run together, each carrying four processors, as cooling fans start on the newly activated boards.
Illustration: AI & Tech News

Microsoft says it reviews model licenses, screens for untrusted code and validates model weights before adding them to the catalog. It also says it builds, scans and signs the serving images, then rolls out software updates to existing deployments.

Custom model serving enters preview

Microsoft also announced preview options for custom models. Teams can deploy registered LoRA adapters produced by Foundry fine-tuning when they match a base-model version and a template that supports LoRA. Multiple adapters can share the GPUs of the deployment hosting them, with a separate deployment name for each.

Bring Your Own Weights is in limited public preview. It lets teams register and deploy custom full-weight SafeTensors models, including models trained outside Foundry, using a compatible catalog base model and a Microsoft-provided template. Microsoft is accepting sign-ups for early access.

What this means

On November 20, 2026, Microsoft introduced Microsoft 365 identities for Foundry agents alongside updates to Managed Compute, which originally launched in public preview in June 2026. Managed Compute deployments include security protocols where Microsoft screens untrusted code, validates model weights, and signs serving images before rolling out software updates to active deployments. Teams scaling traffic can add instances behind existing endpoints, such as expanding a DeepSeek V4.1 Flash (1017) deployment from four to 20 AMD MI300X GPUs across five instances with hourly billing per accelerator. For custom models, early access sign-ups enable registration of full-weight SafeTensors models trained outside Foundry, while fine-tuned LoRA adapters can share hosted GPUs.

Source: Microsoft

Newsletter

Get the best AI & tech news daily

A concise daily digest. Unsubscribe anytime.

We use your email only to send this newsletter.

Keep reading