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.
AI AI Hypercomputer LLM April 6, 2026Boost Training Goodput: How Continuous Checkpointing Optimizes Reliability in Orbax and MaxText - The newly introduced continuous checkpointing feature in Orbax and MaxText is designed to optimize the balance between reliability and performance during model training, addressing issues with conventional fixed-frequency checkpointing. Unlike fixed intervals—which can either compromise reliability or bottleneck performance—continuous checkpointing maximizes I/O bandwidth and minimizes failure risk by asynchronously initiating a new save operation only after the previous one successfully completes. Benchmarks demonstrate that this approach significantly reduces checkpoint intervals and results in substantial resource conservation, especially in large-scale training jobs where mean-time-between-failure (MTBF) is short.
Cloud Spanner Databases Generative AI LLM Official Blog April 6, 2026Spanner's multi-model advantage for the era of agentic AI - Discover how Spanner's unified multi-model database (relational, vector, graph) provides a scalable foundation for agentic AI, eliminating silos and accelerating development.
Generative AI GKE LLM Official Blog April 6, 2026Run real-time and async inference on the same infrastructure with GKE Inference Gateway - GKE Inference Gateway treats accelerator capacity as a fluid resource pool that serves workloads that need deterministic latency and high throughput.
AlloyDB Cloud SQL Generative AI LLM Official Blog April 6, 2026Activating Your Data Layer for Production-Ready AI - Prepare your data for production AI. Explore Google AlloyDB and Cloud SQL labs for semantic search, RAG, multimodal embeddings, AI functions, and NL2SQL query generation.
Gemini LLM Official Blog April 6, 2026Introducing Gemma 4 on Google Cloud: Our most capable open models yet - Today, we’re bringing Gemma 4 to you on Google Cloud, including Vertex AI, Cloud Run, GKE, and Sovereign Cloud.
Generative AI LLM Official Blog April 6, 2026Introducing Veo 3.1 Lite and a new Veo upscaling capability on Vertex AI - The Veo 3.1 family now includes three tiers, all of which feature native audio generation capabilities on Vertex AI.
LLM Official Blog March 30, 2026Five techniques to reach the efficient frontier of LLM inference - Learn the 5 essential techniques—including intelligent L7 routing, quantization, and speculative decoding—to move your LLM inference workloads closer to the efficient frontier, maximizing throughput and minimizing latency without increasing your hardware budget. Discover how to stop overpaying for every token.
Gemini LLM March 23, 2026Video Understanding with Gemini: Notes From the Field - This article outlines architectural strategies for effective video understanding using Google's Gemini models, emphasizing that teaching AI to interpret video is a complex engineering challenge. It proposes a multi-stage agentic workflow, including initial triage and deep analysis, while leveraging audio-first contextualization to enhance accuracy and mitigate hallucination.
Gemini LLM March 16, 2026What you need to know about the Gemini Embedding 2 model - Google's Gemini Embedding 2, now in preview, is its first natively multimodal embedding model, unifying various data types like text, images, and audio into a single API call and joint embedding space.
LLM Official Blog Vertex AI March 16, 2026Build Resilient LLM Applications on Vertex AI and Reduce 429 Errors - Deep dive into Vertex AI’s consumption models and architectural best practices for managing request flows. Use this guide to build smooth, resilient, and truly scalable AI applications.
GCP Experience Generative AI LLM Official Blog March 9, 2026Small models, high quality: Inside BMW Group’s experiments evaluating domain-specific language models - Inside BMW Group’s experiments with building and evaluating domain-specific language models for the automotive sector.
Generative AI LLM Official Blog March 9, 2026The ultimate Nano Banana prompting guide - Learn prompting best practices for Nano Banana Pro and Nano Banana 2, from tech specs to prompting frameworks.
GKE LLM March 2, 2026How to Deploy LLM Inference on GKE — The Parts Tutorials Skip - This article details how to deploy a production-ready LLM inference stack on Google Kubernetes Engine (GKE), tackling common enterprise challenges like VPC policies, organization constraints.
LLM Official Blog March 2, 2026Pro-level image generation gets faster and more accessible with Nano Banana 2 - Nano Banana 2 delivers Pro-level image generation and editing at the speed you expect from Flash — making complex generations faster, cheaper, and more accessible. Available on Vertex AI and the Gemini CLI.
Gemini Generative AI LLM Feb. 23, 2026Hooking up CrewAI with Google Gemini for Multi-Agent Automation Systems - This article demonstrates how to combine the CrewAI framework with Google Gemini models to build advanced multi-agent automation systems. This integration leverages Gemini's rapid reasoning, large context windows, and native Google Search capabilities, enabling AI agents to collaborate effectively on complex tasks.
BigQuery LLM Paywall Feb. 23, 2026BigQuery + Vector Search for Support Tickets: A Practical RAG Pipeline That Survives Real Data Mess - This article details how to construct a practical Retrieval-Augmented Generation (RAG) pipeline for support tickets, specifically designed to handle common data challenges like threads, duplicates, and PII.
Gemini LLM Official Blog Feb. 23, 2026Introducing Gemini 3.1 Pro on Google Cloud - Today, we’re announcing Gemini 3.1 Pro on Google Cloud for developers and business teams. Get started on Gemini CLI, Gemini Enterprise, and Vertex AI.
AI GPU Kubernetes LLM Feb. 16, 2026Part 2 — Exploring DRANET on GKE with B200 GPUs exposed via Inference Gateway - This article details the deployment of Deepseek 3.1 on a Google Kubernetes Engine (GKE) AI Cluster, leveraging B200 GPUs and DRANET for high-performance networking. It provides a step-by-step guide on exposing this large language model for inference via the GKE Inference Gateway, including detailed configuration and validation processes.
Gemini LLM Official Blog Feb. 16, 2026Mastering Model Adaptation: A Guide to Fine-Tuning on Google Cloud - Learn to fine-tune production-ready AI models on Google Cloud: use Vertex AI for Gemini 2.5 Flash, or gain total control by running open-source LLMs like Llama 2 on Google Kubernetes Engine (GKE).
LLM Official Blog Feb. 9, 2026Announcing Claude Opus 4.6 on Vertex AI - Expanding Vertex AI’s curated collection of models with the addition of Anthropic’s newest release: Claude Opus 4.6. Claude Opus 4.6 is Anthropic’s most powerful model yet, outperforming Opus 4.5 across all benchmarks and excelling at complex coding tasks and creating sophisticated agents.
LLM Model Armor Security Feb. 2, 2026Guarding the Gates: A Technical Deep Dive into Model Armor - Model Armor is a critical policy-based security layer that acts as a transparent proxy for Large Language Models, filtering both prompts and responses. This system provides centralized governance, allowing engineering teams to decouple safety logic from application logic for scaled and secure AI deployments.
LLM Feb. 2, 2026Accelerating model refinement: automating Fine-Tuning through checkpoint interpolation with Authentrics Zero Training Optimization & Maintenance (Z-TOM) - This article describes Zero Train Optimization and Maintenance (ZTOM), a new orchestration layer from Authentrics.ai that optimizes AI models like Gemma and Llama 3.2 by mathematically blending existing checkpoints instead of using resource-intensive backpropagation.
Generative AI LLM MCP Jan. 26, 2026Welcome to MCP-P-A-looza - An overview of current Model Context Protocol (MCP) implementations across the programming landscape.
Gemini CLI Generative AI LLM Official Blog Jan. 26, 2026Mastering Gemini CLI: Your Complete Guide from Installation to Advanced Use-Cases - Master Gemini CLI with our free DeepLearning.ai course! Learn to integrate this open-source AI agent for data analysis, content creation, and software development workflows.
Generative AI LLM MCP Jan. 18, 2026The Tool Bloat Epidemic - Strategies for combating tool bloat to improve agent accuracy, latency, and cost.
BigQuery Data Analytics Generative AI LLM Official Blog Jan. 18, 2026Introducing BigQuery managed and SQL-native inference for open models - BigQuery now supports managed and SQL-native inference for Hugging Face and Vertex AI Model Garden open models.
ADK Generative AI LLM Jan. 18, 2026Improve AI output with continuous improvement - This article details how continuous improvement strategies can significantly enhance AI outputs by employing a looping mechanism where AI models iterate on each other's responses.
ADK Generative AI LLM Jan. 12, 2026Improving Cost Visibility for Gemini ADK Agents: Labels and Token Tracking - This article demonstrates how to improve cost visibility for Google's Gemini ADK agents by implementing custom labels and integrating token usage tracking directly within the model class.
GPU LLM TPU Jan. 5, 2026TPU vs GPU: Real-World Performance Testing for LLM Training on Google Cloud - This article provides a deep-dive technical analysis comparing NVIDIA H100 GPUs and Google Cloud's TPUs (v5p) for Large Language Model training.
LLM Model Armor Security Jan. 5, 2026Model Armor integration with Service Extension : introduction to runtime AI security without code changes - This article introduces Google Cloud's Model Armor, a runtime AI protection solution, and details its integration with Service Extensions. This specific integration enables AI security policies to be enforced directly at the load balancer level.
Showing 91–120 of 302 resources
Useful Links
Contact
Třebanická 183
Prague, Czech Republic
Phone: +420 777 283 075
Email: [email protected]