Vishal Bulbule·22h agoGemini Decisions API: A New Approach to Fast and Scalable AI DecisionsGoogle shipped a model that cannot write a sentence. On our runs it answered a yes/no question in 456 ms from pune (India) where an LLM…
InGoogle Cloud - CommunitybyVishal Bulbule·Nov 6Ollama vs vLLM on Cloud Run with an NVIDIA L4: A Real Benchmark from 1 to 48 Concurrent UsersSame GPU, same model. Ollama was 2.4× faster for one user. At 32 users vLLM was 7.7× faster than Ollama’s defaults, and still 3.4× faster…
InGoogle Cloud - CommunitybyVishal Bulbule·Nov 6Self-Hosting Open LLMs on Google Cloud: When It Pays Off, and Which of the Four Options to ChooseA decision framework built on list prices and our own benchmarks: API vs self-hosting, Model Garden vs Cloud Run vs GPU VM vs GKE, and the…
InGoogle Cloud - CommunitybyVishal Bulbule·Nov 6CPU vs GPU for LLM Inference on Cloud Run: A Measured Comparison with Gemma and an NVIDIA L4Same model, same container, same platform: the GPU was 13.5× faster per token and 6× cheaper per answer, though it costs twice as much per…A response icon1A response icon1
Vishal Bulbule·Jul 27How to Generate Architecture Diagrams in Google Antigravity using MCP serverGoogle Antigravity is an agentic IDE — the agent plans, edits, and runs code for you. What it doesn’t do out of the box is draw. When you…A response icon1A response icon1
InGoogle Cloud - CommunitybyVishal Bulbule·Jul 8Building AI-Powered search App with Elastic ,Google Gemini & ADKOpen ChatGPT or Gemini and ask it something only your company would know — say, how many weeks of parental leave your primary caregivers…
InGoogle Cloud - CommunitybyVishal Bulbule·Jul 1Agent Development Kit (ADK) Deployment GuideThis guide provides a central overview of deployment options, setup procedures, and a decision matrix for hosting your Agent Development…A response icon1A response icon1
InGoogle Cloud - CommunitybyVishal Bulbule·Jun 24Google Gemini Enterprise Agent Platform Tutorial: Registering ADK AgentsIf you’ve been following Google Cloud lately, you’ve probably seen the name Gemini Enterprise everywhere — and maybe a little confusion…
InGoogle Cloud - CommunitybyVishal Bulbule·Jun 22Building AI Agents with Google Cloud Managed MCP Servers and ADKWhat is MCP?A response icon1A response icon1
Vishal Bulbule·Jun 22Manage Your Entire Google Cloud with AI Agents | AgenticOps DemoHow We Built AgenticOps Using Google ADK, MCP Servers & Gemini.
