Ammett W – Medium

Ammett W

Pinned

Published in

Networking in Google Cloud — Monthly catch up -’2025 edition (monthly updates)

Updated every month for ‘2025 — — — — — — — — — — — — — —

Jan 28

Networking in Google Cloud — Monthly catch up -’2025 edition (monthly updates)

Jan 28

Pinned

Published in

Connecting to Cloud SQL via Private Service Connect — Private connectivity made easy

Connecting to your managed SQL database privately just got a whole lot easier. Learn with these labs

Jan 17

Connecting to Cloud SQL via Private Service Connect — Private connectivity made easy

Jan 17

Published in

Configure Gemini CLI on Google Compute Engine (GCE) with private connectivity

AI-powered tools like the Gemini command-line interface (CLI) are transforming developer workflows, bringing the power of advanced models…

Oct 7

Configure Gemini CLI on Google Compute Engine (GCE) with private connectivity

Oct 7

Published in

AI Inferencing — Serve DeepSeek v3.1 Base on Google Cloud A4 (B200 GPUs) using vLLM and GKE

DeepSeek changed the LLM game when it was first released. In this blog demo you’ll run the new DeepSeek v 3.1 Base model on…

Sep 30

AI Inferencing — Serve DeepSeek v3.1 Base on Google Cloud A4 (B200 GPUs) using vLLM and GKE

Sep 30

Published in

AI/Infra — Serve gpt-oss-120b on Google Cloud A4 (B200 GPUs) using vLLM and GKE

Everyone loves gpt, now we have models like gpt-oss!! Today, we’re diving into a practical guide that will show you exactly how to deploy…

Aug 20

AI/Infra — Serve gpt-oss-120b on Google Cloud A4 (B200 GPUs) using vLLM and GKE

Aug 20

Published in

AI/Infra Inferencing — Serve Qwen 3 235B Thinking on Google Cloud A4 (B200 GPUs) using vLLM and GKE

Qwen 3 what is that? Qwen is a LLM from Alibaba with and open licenses and is also available on Hugging face. In this blog demo you’s run…

Aug 20

AI/Infra Inferencing — Serve Qwen 3 235B Thinking on Google Cloud A4 (B200 GPUs) using vLLM and GKE

Aug 20

Published in

Inferencing — Serve Llama 4 on A4 (B200 GPUs) using VLLM and GKE

The worlds of Artificial Intelligence and high-performance computing are not just colliding; they’re fusing. With state-of-the-art…

Aug 13

Inferencing — Serve Llama 4 on A4 (B200 GPUs) using VLLM and GKE

Aug 13

Published in

Part III — Deploy Gemma workloads on A3 Ultra with H200 GPUs on GKE : (3) Inferencing

In part I we introduced the topics of RDMA, in part II we deployed a RDMA VPC, A3 Ultra node with H200 GPU in a GKE cluster.

Aug 1

Part III — Deploy Gemma workloads on A3 Ultra with H200 GPUs on GKE : (3) Inferencing

Aug 1

Published in

Part II— RoCEv2 VPC deployment on Google Cloud : (2) Steps and Choices?

Lets explore option to deploy A3 ultra (H200 GPU) node cluster with and RDMA VPC on GKE … options and demo

Jul 15

Part II— RoCEv2 VPC deployment on Google Cloud : (2) Steps and Choices?

Jul 15

Published in

Part I - RoCEv2 for optimized GPU AI workloads on Google Cloud : (1) Why it matters?

I’ve began my career in standard networks, I’ve listen to the buzz on Digital Transformation, I’ve explored Cloud and now it’s AI’s turn…

Jun 26

Part I - RoCEv2 for optimized GPU AI workloads on Google Cloud : (1) Why it matters?

Jun 26

Ammett W

Ammett W

DevRel Cloud AI Infra/Networking @ Google | Founder of Start Cloud Now | CCIE#43659, CISSP, Inspiring people as I go along my journey. Learn, Do your best.

Following

Help

Status

About

Careers

Press

Blog

Privacy

Rules

Terms

Text to speech