対面イベント

Red Hat at Google Cloud Next 2026

2026 年 4 月 22 日 - 2026 年 4 月 24 日 Las Vegas, NVMandalay Bay Convention Center
Event menu

Red Hat and Google Cloud: Simplify your journey to the cloud

Are you attending Google Cloud Next? Visit the Red Hat booth to meet with our open source experts and learn how Red Hat and Google Cloud work together to speed cloud migration and enhance cloud operations so you can focus on business innovation.

red hat google cloud

Red Hat Mini-Theater

We look forward to you joining us for mini-theater sessions at the Red Hat booth #2517 throughout the week! 

Wednesday, April 22

11:15 am

TBA

(Red Hat booth)

11:45 am

AIOps on Google Cloud

(Red Hat booth)

Explore the critical role of Ansible Automation Platform in enabling AIOps for self-healing infrastructure on Google Cloud by integrating issue detection and automated remediation. We will show how the Red Hat Ansible Automation Platform provides the event-driven architecture necessary to centralize and execute rapid, intelligent responses. Learn practical strategies for leveraging event-driven workflows to enhance system resilience, and achieve a truly autonomous operational environment.

Hicham Mourad,

Red Hat

2:00 pm

Scaling LLM Inference on Google Cloud

(Red Hat booth)

"Scaling LLM inference in production is no longer just a hardware challenge. It is a distributed systems challenge. llm-d is a Kubernetes-native, high-performance distributed LLM inference framework built on vLLM. It provides a well-lit path to serve models at scale with fast time-to-value and competitive performance per dollar across GPUs, TPUs, and hybrid environments. This talk introduces llm-d’s architecture, including the Inference Gateway for intelligent routing and latency-aware scheduling, and shares real-world results such as 60k+ tokens per second throughput and up to 3x P90 latency improvements. Scaling LLM inference in production is no longer just a hardware challenge. It is a distributed systems challenge. llm-d is a Kubernetes-native, high-performance distributed LLM inference framework built on vLLM. It provides a well-lit path to serve models at scale with fast time-to-value and competitive performance per dollar across GPUs, TPUs, and hybrid environments. This talk introduces llm-d’s architecture, including the Inference Gateway for intelligent routing and latency-aware scheduling, and shares real-world results such as 60k+ tokens per second throughput and up to 3x P90 latency improvements. If you are running LLMs in production and care about scale, cost, and operational simplicity, llm-d offers a proven foundation.

Sawyer Bowerman,

Red Hat

2:30 pm

Orchestrating Vertex AI on Google Cloud

(Red Hat booth)

To overcome the operational roadblocks of scaling enterprise AI, the Red Hat Ansible Certified Content Collection for Google Cloud now includes native support for Vertex AI. Red Hat Ansible Automation Platform replaces this fragmented, manual deployment processes with declarative, version-controlled automation. As a result, IT operations teams can seamlessly collaborate to reliably accelerate the transition of models from the lab to production.

Matthew Packer,

Red Hat

3:00 pm

OpenShift Virtualization on Google Cloud

(Red Hat booth)

Learn how you migrate and modernize your VMs with a fully managed application platform, Red Hat OpenShift Dedicated on Google Cloud. OpenShift Dedicated provides a comprehensive platform for modernizing VM based workloads with cloud-native technologies, reducing operational complexity while accelerating innovation.

Shreyans Mulkutkar,

Red Hat

3:30 pm

OpenShift Virt on NetApp on Google Cloud

(Red Hat booth)

Jim Chang,

NetApp

4:00 pm

TBA

(Red Hat booth)

Thursday, April 23

10:00 am

TBA

(Red Hat booth)

10:30 am

Orchestrating Vertex AI on Google Cloud

(Red Hat booth)

To overcome the operational roadblocks of scaling enterprise AI, the Red Hat Ansible Certified Content Collection for Google Cloud now includes native support for Vertex AI. Red Hat Ansible Automation Platform replaces this fragmented, manual deployment processes with declarative, version-controlled automation. As a result, IT operations teams can seamlessly collaborate to reliably accelerate the transition of models from the lab to production.

Matthew Packer,

Red Hat

11:00 am

TBA

(Red Hat booth)

11:30 am

Scaling LLM Inference on Google Cloud

(Red Hat booth)

Scaling LLM inference in production is no longer just a hardware challenge. It is a distributed systems challenge. llm-d is a Kubernetes-native, high-performance distributed LLM inference framework built on vLLM. It provides a well-lit path to serve models at scale with fast time-to-value and competitive performance per dollar across GPUs, TPUs, and hybrid environments. This talk introduces llm-d’s architecture, including the Inference Gateway for intelligent routing and latency-aware scheduling, and shares real-world results such as 60k+ tokens per second throughput and up to 3x P90 latency improvements. If you are running LLMs in production and care about scale, cost, and operational simplicity, llm-d offers a proven foundation.

Sawyer Bowerman,

Red Hat

2:00 pm

TBA

(Red Hat booth)

2:30 pm

TBA

(Red Hat booth)

3:00 pm

OpenShift Virtualization on Google Cloud

(Red Hat booth)

Learn how you migrate and modernize your VMs with a fully managed application platform, Red Hat OpenShift Dedicated on Google Cloud. OpenShift Dedicated provides a comprehensive platform for modernizing VM based workloads with cloud-native technologies, reducing operational complexity while accelerating innovation.

Shreyans Mulkutkar,

Red Hat

3:30 pm

UPS's Critical Customer Care Automation (CCCA) initiative uses IBM WatsonX hosted on Red Hat OpenShift Dedicated on Google Cloud.

(Red Hat booth)

Dustin Trapani,

Red Hat

Ganga Dhar Timilsina,

UPS

4:00 pm

AIOps on Google Cloud

Explore the critical role of Ansible Automation Platform in enabling AIOps for self-healing infrastructure on Google Cloud by integrating issue detection and automated remediation. We will show how the Red Hat Ansible Automation Platform provides the event-driven architecture necessary to centralize and execute rapid, intelligent responses. Learn practical strategies for leveraging event-driven workflows to enhance system resilience, and achieve a truly autonomous operational environment.

Hicham Mourad,

Red Hat

4:30 pm

TBA

(Red Hat booth)

Red Hat has been the trusted centerpiece in our transformation to a composable IT architecture.

Justin Boitano

Steen Kronborg Chief Enterprise Architect, Salling Group

Exclusive Branded Merchandise: Available While Supplies Last

A limited supply of our signature red hats will be available. We encourage you to stop by promptly to secure your item and connect directly with our onsite team.

Show Information

Show Location: Mandalay Bay Convention Center

Show Address:

    3950 S Las Vegas Blvd, Las Vegas, NV 89119

Show Dates: April 22-24, 2026

Expo Hours (PST):

      Wednesday, April 22: 9:00 PM – 6:00  PM

      Thursday, April 23: 9:00 PM – 5:30  PM

      Friday, April 24: 9:00 PM – 2:00  PM

Red Hat Booth: 2517

Mandalay Bay - Map of Las Vegas

Open Unlocks the World's Potential

At Red Hat, our commitment to open source extends beyond technology into virtually everything we do. We collaborate and share ideas, create inclusive communities, and welcome diverse perspectives from all Red Hatters, no matter their role. It’s what makes us who we are. Join us. At Red Hat, opportunities are open

Social

Follow along on Twitter