Skip to main content

Solutions
Products
AI Inference
Buoyant AI
Run frontier-grade open-weight models with unlimited tokens and full inference control.
Kinference [kay-inference]
The open source inference control plane for vLLM and Kubernetes.
Enterprise Service Mesh
Buoyant Enterprise for Linkerd
Enterprise-grade security and compliance for production infrastructure.
Linkerd
CNCF open source security for every Kubernetes cluster.
The AI Kubernetes Show
The Kubernetes AI Show dives deep into the real-world challenges of adopting AI on Kubernetes platforms.
Watch now
Use Cases
AI Inference
Cut coding inference spend
Move agentic coding to open-weight models running on GPUs you control.
Burst to the cloud when your GPUs are full
When GPUs saturate, excess requests burst to the cloud.
Get full efficiency from every GPU
More useful work from every GPU, even at peak utilization.
Every app, model, tenant gets an SLO
Cache-aware routing that predicts latency and holds every tenant’s SLOs.
Intent-based routing
Serve every prompt based on its context.
Enterprise Service Mesh
FIPS for FedRAMP, CMMC, and HIPAA
A validated control plane and data plane, audit-ready in 90 days
Zero trust in Kubernetes
Strict mTLS and deny-by-default policy for every workload
Multicluster and failover
Federated services and cross-cluster mTLS for migrations
Cross-zone cost reduction
HAZL keeps healthy traffic in-zone and cuts transfer costs
Observability and reliability
Golden metrics, automated cert rotation, and OpenTelemetry tracing
The AI Kubernetes Show
The Kubernetes AI Show dives deep into the real-world challenges of adopting AI on Kubernetes platforms.
Watch now
Pricing
Resources
Runbook
Live fireside chats, demos, AMAs, and lessons learned, as well as self-paced labs and a hands-on escape room.
Explore Runbook
Runbook
Live fireside chats, demos, AMAs, and lessons learned as well as self-paced labs.
Case studies
Learn how organizations across the world run Linkerd in production.
Ebooks, videos and resources
Enterprise-focused documents to better inform you about the service mesh
Buoyant Linkerd forum
Get support for Linkerd from the maintainers, experts, and Linkerd community!
Linkerd vs Istio
How do the two service meshes compare?
Linkerd vs Cilium
Five Key Differences in 2025
Guide to mTLS and Kubernetes
A Kubernetes engineer's guide to mutual TLS.
Blog
About
About us
Our mission and our story
Partners
Meet our partners, or become one. Together, we help teams worldwide use Linkerd with confidence.
Contact us
Have a question or ready to get started with Linkerd?
Careers
Our mission and our story
Newsroom
The latest news about the service mesh

Contact us Docs

Announcing Kinference: Scalable inference serving for Kubernetes |

Buoyant announces a new open-source project for scalable inference platforms on Kubernetes.

Nov 9, 2026

Get started with Buoyant Enterprise for Linkerd

Installation guide for Buoyant Enterprise for Linkerd

Get started for free Contact us

A structured path from frontier APIs to self-hosted inference

We're working with engineering organizations today through structured proofs of concept that guide them towards cost-efficient self-hosted inference.

Move your coding agents onto infrastructure you control

Buoyant AI runs on the GPU clusters you already own

Run inference the way you run everything else

It’s open source. Turn the GPU clusters you already run into an inference platform.

Inference Use Cases

Cut coding inference spend Burst to the cloud when your GPUs are full Get full efficiency from every GPU in the pool Every app, model, and tenant gets an SLO Intent-based routing See all use cases

Products

Buoyant Enterprise for Linkerd Linkerd [linker-d]Buoyant AI Kinference [kay-inference]

Resources

Case studies Ebooks & Videos Pricing Articles

Runbook

Labs- Self-paced courses Live - Fireside chats & AMA

Company

About Us Newsroom Partners Contact Us Careers

Privacy Policy

|

Cookie Policy

|

Cookie Preferences

Get started with Buoyant Enterprise for Linkerd

Installation guide for Buoyant Enterprise for Linkerd

Get started for free Contact us

A structured path from frontier APIs to self-hosted inference

We're working with engineering organizations today through structured proofs of concept that guide them towards cost-efficient self-hosted inference.

Move your coding agents onto infrastructure you control

Buoyant AI runs on the GPU clusters you already own

Run inference the way you run everything else

It’s open source. Turn the GPU clusters you already run into an inference platform.

Inference Use Cases

Cut coding inference spend Burst to the cloud when your GPUs are full Get full efficiency from every GPU in the pool Every app, model, and tenant gets an SLO Intent-based routing See all use cases

Products

Buoyant Enterprise for Linkerd Linkerd [linker-d]Buoyant AI Kinference [kay-inference]

Resources

Case studies Ebooks & Videos Pricing Articles

Runbook

Labs- Self-paced courses Live - Fireside chats & AMA

Company

About Us Newsroom Partners Contact Us Careers

Privacy Policy

|

Cookie Policy

|

Cookie Preferences

Get started with Buoyant Enterprise for Linkerd

Installation guide for Buoyant Enterprise for Linkerd

Get started for free Contact us

A structured path from frontier APIs to self-hosted inference

We're working with engineering organizations today through structured proofs of concept that guide them towards cost-efficient self-hosted inference.

Move your coding agents onto infrastructure you control

Buoyant AI runs on the GPU clusters you already own

Run inference the way you run everything else

It’s open source. Turn the GPU clusters you already run into an inference platform.

Inference Use Cases

Cut coding inference spend Burst to the cloud when your GPUs are full Get full efficiency from every GPU in the pool Every app, model, and tenant gets an SLO Intent-based routing See all use cases

Products

Buoyant Enterprise for Linkerd Linkerd [linker-d]Buoyant AI Kinference [kay-inference]

Resources

Case studies Ebooks & Videos Pricing Articles

Runbook

Labs- Self-paced courses Live - Fireside chats & AMA

Company

About Us Newsroom Partners Contact Us Careers

Privacy Policy

|

Cookie Policy

|

Cookie Preferences

Get started with Buoyant Enterprise for Linkerd

Installation guide for Buoyant Enterprise for Linkerd

Get started for free Contact us

A structured path from frontier APIs to self-hosted inference

We're working with engineering organizations today through structured proofs of concept that guide them towards cost-efficient self-hosted inference.

Move your coding agents onto infrastructure you control

Buoyant AI runs on the GPU clusters you already own

Run inference the way you run everything else

It’s open source. Turn the GPU clusters you already run into an inference platform.

Inference Use Cases

Cut coding inference spend Burst to the cloud when your GPUs are full Get full efficiency from every GPU in the pool Every app, model, and tenant gets an SLO Intent-based routing See all use cases

Products

Buoyant Enterprise for Linkerd Linkerd [linker-d]Buoyant AI Kinference [kay-inference]

Resources

Case studies Ebooks & Videos Pricing Articles

Runbook

Labs- Self-paced courses Live - Fireside chats & AMA

Company

About Us Newsroom Partners Contact Us Careers

Privacy Policy

|

Cookie Policy

|

Cookie Preferences

Get started with Buoyant Enterprise for Linkerd

Installation guide for Buoyant Enterprise for Linkerd

Get started for free Contact us

A structured path from frontier APIs to self-hosted inference

We're working with engineering organizations today through structured proofs of concept that guide them towards cost-efficient self-hosted inference.

Move your coding agents onto infrastructure you control

Buoyant AI runs on the GPU clusters you already own

Run inference the way you run everything else

It’s open source. Turn the GPU clusters you already run into an inference platform.

Inference Use Cases

Cut coding inference spend Burst to the cloud when your GPUs are full Get full efficiency from every GPU in the pool Every app, model, and tenant gets an SLO Intent-based routing See all use cases

Products

Buoyant Enterprise for Linkerd Linkerd [linker-d]Buoyant AI Kinference [kay-inference]

Resources

Case studies Ebooks & Videos Pricing Articles

Runbook

Labs- Self-paced courses Live - Fireside chats & AMA

Company

About Us Newsroom Partners Contact Us Careers

Privacy Policy

|

Cookie Policy

|

Cookie Preferences

‍By clicking “Accept,” you agree to our privacy policy and the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts.

Preferences Reject Accept

Manage Consent Preferences by Category

Essentials

Always active

Necessary for the site to function. Always On.

Marketing

Used for targeted advertising.

Personalization

Remembers your preferences and provides enhanced features.

Analytics

Measures usage and improves your experience.

Reject All Accept All

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Preferences