[ Scrolls & chronicles ]Migration from Codea Bien
Blog
What I measured and what I learned.
- OCT 2026Angular #vllm #ai
Quantization for vLLM: FP8, INT4 and NVFP4 without losing the plot
You didn't quantize your 30B FP8 checkpoint: you downloaded it from Hugging Face with the -FP8 suffix. That's the right call 90% of the time. The interesting quantization starts wh…
4 min // 200 xp
- OCT 2026Angular #vllm #ai
KV cache that doesn't fit: offloading in vLLM, from file to object
Your multi-turn agents resend the full history every turn, and prefix caching saves you as long as sessions fit the GPU. The problem arrives when the number of conversations grows:…
3 min // 150 xp
- OCT 2026Angular #webmcp #angular 22
WebMCP in Angular: your app as a toolbox for AI agents
Your Angular application can now register tools that an AI agent discovers and executes without ever leaving the page. The feature is called WebMCP, it shipped as experimental in A…
8 min // 400 xp
- OCT 2026Angular #angular 22 #incremental hydration
Angular 22: incremental hydration by default and resource caching in SSR
You ran ng update to Angular 22 and incremental hydration is now active without touching a line. If your app already used provideClientHydration(), the commit "make incremental hyd…
6 min // 300 xp
- OCT 2026#typescript 7 #tsgo
TypeScript 7 GA: the reality of the Go port
On July 8, 2026, Microsoft shipped TypeScript 7.0, and the industry's most-used compiler changed languages. The JavaScript codebase, codenamed "Strada", hands the baton to "Corsa",…
6 min // 300 xp
- OCT 2026#vite 8 #rolldown
Vite 8 and Rolldown: the VoidZero stack that wants to own your build
46 seconds down to 6. That's Linear's production build after migrating to Vite 8. Ramp reports -57% on their builds, Beehiiv -64%. The version that makes that possible shipped on M…
6 min // 300 xp
- OCT 2026Angular #angular 22 #typescript 7
Angular and TypeScript 7 (tsgo): the 10x compiler you can't use yet
The TypeScript compiler now runs between 7.7x and 11.9x faster as of July. Angular still can't use it. Version 7.0 went GA on July 8, 2026 with the compiler rewritten in Go, but An…
6 min // 300 xp
- OCT 2026AI #ollama #modelo local
Your First Local Model in 10 Minutes (Ollama)
Before renting a single GPU, let's run a model on your own machine. Free, no account, 10 minutes. The goal isn't production: it's understanding the full request-to-tokens cycle, wh…
4 min // 200 xp
- OCT 2026AI #vllm troubleshooting #errores gpu alquilada
When It Explodes: The 7 Errors of Serving vLLM on a Rented GPU
Your server will fail. That's not pessimism, it's statistics: you rented an ephemeral container, downloaded 31 GB of weights, and started three services that met each other today.…
4 min // 200 xp
- OCT 2026AI #stitch cli #google stitch
Stitch CLI: Google Brings UI Design to the Terminal (and to Your Agent)
Google has introduced Stitch CLI, a command-line tool (@google/stitch) that brings Stitch's generative UI design to the terminal and to your coding agent. The official promise: "yo…
11 min // 550 xp