Tag: LLM
Resources about LLM collected from the weekly GCP Weekly newsletter — a hand-curated collection of Google Cloud Platform news, technical articles, tutorials, videos and release notes. Each entry below links back to the original GCP Weekly issue and retains its publish date and title, giving you a focused, searchable knowledge base for this topic.
Billing FinOps Gemini LLM Startups Vertex AI Dec. 22, 2025The Unit Economics of Virality: How We Scaled Gemini 1.5 Pro to 50k Users Without Going Bankrupt - Buy unused credits with a discount.
ADK GKE GKE Autopilot LLM Dec. 15, 2025ADK Agents on GKE with Self-Hosted LLMs & vLLM - This tutorial demo deploying Llama-3.1–8B-Instruct model on Google Kubernetes Engine (GKE) using vLLM and integrating an ADK Agent.
AI Generative AI LLM Security Dec. 1, 2025How Vertex AI RAG Engine Simplifies Security Policy Grounding and Multi-Corpus Architecture - My experience of exploring GCP RAG Engine for security-related tasks.
LLM Official Blog Dec. 1, 2025Announcing Claude Opus 4.5 on Vertex AI - Anthropic’s newest model, Claude Opus 4.5, is generally available on Vertex AI. As Anthropic’s most advanced model to date, it excels in coding, agents, vision, computer use and office tasks — at one-third the cost of its predecessor, Opus 4.1.
GKE LLM Official Blog Nov. 17, 2025Running high-scale reinforcement learning (RL) for LLMs on GKE - Learn about Google Cloud's full-stack, integrated approach, from custom TPU hardware to the GKE orchestration layer – and shares how you can solve the hybrid, high-stakes demands of RL at scale.
GKE LLM Official Blog Nov. 10, 2025Boosting LLM Performance with Tiered KV Cache on Google Kubernetes Engine - Boost LLM inference performance with LMCache on Google Kubernetes Engine. Discover how tiered KV cache expands NVIDIA GPU HBM with CPU RAM and local SSDs, significantly improving context length, concurrency, and throughput for large language models.
Generative AI Infrastructure LLM Machine Learning Oct. 27, 2025Training Nanochat on a A3 Spot VM - This article explains how to train a nanochat model, a simplified LLM implementation, on Google Cloud using an A3 Spot VM to leverage spare capacity at a significantly reduced cost.
Agents Cloud Trace LLM Vertex AI Oct. 20, 2025Tracing Your AI Agents for Better Observability: A Guide with Agent Engine - This guide explains how to use tracing with Agent Engine on Vertex AI to understand AI agent decision-making. It covers key concepts like traces, spans, and attributes, and demonstrates how to enable tracing, analyze data with the Cloud Trace SDK and pandas, and clean up resources.
Infrastructure LLM Oct. 20, 2025Build Your Own AI Hypercomputer: Training Qwen2 on a Slurm Cluster - The article provides a guide on building a high-performance Slurm cluster on Google Cloud using the Cluster Toolkit to train a 1.5 billion parameter Qwen2 model.
Generative AI LLM Official Blog Vertex AI Oct. 20, 2025Introducing LLM-Evalkit: A practical framework for prompt engineering on Google Cloud - LLM-Evalkit is a light-weight, open-source application designed to bring structure to this process. LLM-Evalkit is a practical lightweight framework built on Vertex AI SDKs using Google Cloud that centralizes and streamlines prompt engineering.
Generative AI LLM Official Blog Oct. 20, 2025The ultimate prompting guide for Veo 3.1 - This guide is a framework for directing Veo 3.1, our latest model. Veo 3.1 is state-of-the-art and builds on Veo 3, with stronger prompt adherence and improved audiovisual quality when turning images into videos.
Generative AI LLM Official Blog Vertex AI Oct. 20, 2025Announcing prompt management in the Vertex AI SDK - Today, we are announcing the General Availability (GA) of Prompt Management in the Vertex AI SDK, a new set of capabilities designed to bring control, scalability, and enterprise-readiness to your prompt management workflow.
Gemini CLI GKE LLM Official Blog Oct. 20, 2025Use Gemini CLI to deploy cost-effective LLM workloads on GKE - Google Kubernetes Engine (GKE) offers Inference Quickstart. With Inference Quickstart, you can replace months of manual trial-and-error with out-of-the-box manifests and data-driven insights. Learn more today.
ADK Cloud Spanner Generative AI LLM Oct. 13, 2025Building a RAG agent using Google ADK + Spanner - The article explains how to build Retrieval Augmented Generation (RAG) agents using Google Agent Development Kit (ADK) and Spanner, a globally distributed database.
Generative AI LLM Official Blog Partners Oct. 6, 2025Announcing Claude Sonnet 4.5 on Vertex AI - Announcing Claude Sonnet 4.5 on Vertex AI, Anthropic's most intelligent model for complex agents, coding, and computer use, is now available on Google Cloud.
GKE Kubernetes LLM Sept. 8, 2025Serving Gemma 3 on GKE with TPUs and vLLM - Learn how to deploy Gemma 3 model on GKE using TPUs and vLLM.
Generative AI LLM Sept. 1, 2025Building a Multi-Agent Travel Agency with MCP Toolbox for Databases - Automating Travel Planning with Intelligent Agents and Database Integration.
LLM Machine Learning TPU Sept. 1, 2025Using Google’s AI Hypercomputer - Fine Tuning Gemma 3 using MaxText and XPK.
AI LLM Sept. 1, 2025How I Built a Recipe Parser That Actually Works Using Google’s LangExtract - The author describes building a recipe parser using Google's LangExtract library, which leverages LLMs to extract structured data from unstructured text.
GPU LLM Official Blog Sept. 1, 2025vLLM Performance Tuning: The Ultimate Guide to xPU Inference Configuration - Optimize vLLM serving for LLMs on GPUs and TPUs. This guide details selecting accelerators, configuring vLLM, and benchmarking for the best cost-performance ratio for your specific use case.
Gemini LLM Streaming Aug. 18, 2025Agent Engine with Gemini BiDi Streaming Session Workaround - Real time voice interaction is the best way to interact with agent. But agent engine is not ready yet. How to go beyond the limitations?
GKE LLM Official Blog Aug. 18, 2025Run OpenAI’s new gpt-oss model at scale with Google Kubernetes Engine - We’re announcing immediate support for deploying gpt-oss-120b and gpt-oss-20b on GKE. We are also giving customers detailed benchmarks of gpt-oss-120b on accelerators on Google Cloud.
Gemini LLM Official Blog Tutorial Aug. 18, 2025Tutorial: How to use the Gemini Multimodal Live API for QA - This tutorial will show you how to leverage the Gemini API to build an automated quality inspection system that overcomes the common challenges of manual QA.
GPU LLM Aug. 4, 2025Serving Gemma 3 on A2 Machines using vLLM - Learn how to host inference service on GPU powered machine in Google Cloud using Gemma 3 and vLLM!
Infrastructure LLM TPU Aug. 4, 2025Serving Gemma 3 on TPU v5e and v6e using vLLM - Learn how to serve Gemma 3 27B on v5e and v6e TPU VMs!
Apigee Gemini LLM Aug. 4, 2025Harnessing Apigee API Management Platform as an LLM Gateway: Implementation Walkthrough (Part 2/2) - The article provides a step-by-step guide on implementing an LLM gateway using Apigee, detailing the setup of a backend service on Google Cloud Run for interacting with various LLMs (Gemini, OpenAI, Anthropic), configuring Apigee for security, prompt sanitization, and traffic management, and deploying a Streamlit frontend for user interaction, while also emphasizing the importance of analytics and monitoring for cost management and monetization.
AI LLM Aug. 4, 2025Fine-tuning Gemma 3 on an A3 Mega Slurm Cluster - This article demonstrates fine-tuning the Gemma 3 language model on a multi-node, multi-GPU Slurm cluster on Google Cloud using the Google Cloud Cluster Toolkit, Hugging Face Accelerate, and FSDP for distributed training.
AI LLM Aug. 4, 2025Fine-tuning Gemma 3 on an A4 Slurm Cluster - This article demonstrates how to fine-tune the Gemma 3 language model on a multi-node, multi-GPU Slurm cluster on Google Cloud using the Google Cloud Cluster Toolkit.
ADK LLM Aug. 4, 2025Building a Medical RAG System with Google’s Agent Technologies: A Complete Implementation Guide - The article details the implementation of a Retrieval-Augmented Generation (RAG) system on Google Cloud Platform for medical customer support.
AI LLM Official Blog Aug. 4, 2025Veo 3 and Veo 3 Fast are now generally available on Vertex AI - Building on momentum with Veo 3 by making Veo 3 available for everyone on Vertex AI, and announcing Veo 3 Fast, a model designed for speed and rapid iteration. Try Veo 3 today.
Showing 121–150 of 302 resources
Useful Links
Contact
Třebanická 183
Prague, Czech Republic
Phone: +420 777 283 075
Email: [email protected]