Going Offline: Self-Hosting LinguaLive with Gemma 4, Parakeet, Supabase & Qdrant
Published: July 6, 2026 14:58
A follow-up to A 28cm-tall Multilingual Tutor: Building LinguaLive with Reachy Mini & Gemini Live APIContinue reading on Medium »
@medium.com.renjithvr11.source.rss-75adf83cb486------2@rss-parrot.net
I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.
---
Stories by Renjith Ravindranathan on Medium
Site URL: medium.com/@renjithvr11?source=rss-75adf83cb486------2
Feed URL: medium.com/feed/@renjithvr11
Posts: 10
Followers: 1
Going Offline: Self-Hosting LinguaLive with Gemma 4, Parakeet, Supabase & Qdrant
Published: July 6, 2026 14:58
A follow-up to A 28cm-tall Multilingual Tutor: Building LinguaLive with Reachy Mini & Gemini Live APIContinue reading on Medium »
Ship to the Edge, Safely: A Guardrailed Cloudflare Deploy Built with Superplane
Published: June 30, 2026 21:21
“Deploys should stay one click — but that click should be verified, alerted, and recorded.”Continue reading on DevOps.dev »
Databricks CI/CD from Scratch: Asset Bundles, Azure Pipelines, and Airflow on Kubernetes
Published: June 20, 2026 08:29
Two LLMs, One GPU, and a Smart Router: Building an Agentic Stack on Kubernetes
Published: June 6, 2026 16:20
A walkthrough of vLLM, the Semantic Router, and Agentgateway — with all the bits the docs leave out.Continue reading on Towards AI »
Building an AI Gateway with LiteLLM on Kubernetes
Published: May 26, 2026 21:06
If you’re just landing here, catch up with Part 1 and Part 2: Serverless GPUs, KEDA scale-to-zero, llama.cpp and observability. Every…Continue reading on Level Up Coding »
The Agentic OS: A Platform Engineer’s Deep Dive into Notion Workers
Published: May 15, 2026 07:10
Don’t have a Medium subscription? No worries — you can read this article for free using this link.Continue reading on Medium »
Serverless GPUs : KEDA scale-to-zero, llama.cpp and Observability
Published: April 29, 2026 18:41
Part 2 of my series on running TurboQuant-flavoured llama.cpp on a homelab Kubernetes cluster. If you missed Part 1, where I covered the…Continue reading on Medium »
llama.cpp + TurboQuant on Kubernetes: A Beginner-Friendly Guide to the 3.5-Bit Revolution
Published: April 17, 2026 23:33
If you’ve ever tried to run a massive Large Language Model (LLM) on your own hardware, you know the heartbreak of the “out of memory”…Continue reading on Medium »
Supercharging Claude Code DX: Solving Context Bloat and AI Amnesia with Graphify and Ogham MCP
Published: April 8, 2026 18:17
Don’t have a Medium subscription? No worries — you can read this article for free using this link.Continue reading on Medium »
I Set Up a Sandboxed AI Agent on Ubuntu Using NemoClaw and Amazon Bedrock.
Published: March 20, 2026 21:24
A step-by-step walkthrough of NemoClaw, OpenShell, and LiteLLM with Amazon Nova Lite 2 on BedrockContinue reading on Medium »