Blog

Thoughts & Stories

Sharing my experiences, learnings, and adventures in tech and beyond.

Browse by Topic

DevOps & Cloud Infrastructure (193)AI & LLMs (143)Backend & APIs (102)Web Development (90)ERP Systems (77)Security (65)Software Development (58)Career Reflections (29)Cloud (29)AI / Machine Learning (18)Product & SaaS (12)University (1)Hackathons (1)

AI/MLOctober 202612 min read

vLLM 0.31 Release Notes: Preload, Model Runner V2 and the Flags That Break

A close reading of the vLLM v0.29, v0.30 and v0.31 release pages and the preload docs: the weight-cache daemon that makes restarts fast, where it silently falls back to disk, and the removed flags to grep for first.

AI/MLOctober 202612 min read

vLLM Bi-Directional KV Transfer for Multi-Turn Agents

Multi-turn agents resend their whole history, and a disaggregated prefill node recomputes what the decode node already holds. A close reading of vLLM's bi-directional KV transfer: the six steps, the TTL and threshold knobs, the numbers and what breaks.

AI/MLOctober 202612 min read

vLLM Disaggregated Prefill Decode: A NixlConnector Guide

How to split vLLM into prefill and decode instances with NixlConnector, what vLLM's own L40S goodput numbers show, and the transfer checks that stop you benchmarking a broken setup.

AI/MLOctober 202612 min read

vLLM NixlPushConnector: Push vs Pull KV Transfer and TTFT

vLLM's push-based KV transfer registers decode blocks early and lets prefill write them, cutting TTFT roughly 3x in its own test. A close reading of the mechanism, the numbers, the failure modes and when pull still wins.

DevOpsOctober 202616 min read

Anthropic Replaced Git With Scion: What Agent-Scale Source Control Changes

Claude pushed Anthropic's monorepo from 2,500 to over 30,000 merges a day, and git could not keep up. A close reading of Scion's design, its own figures and numbers, and what teams that will never hit that scale should copy.

DevOpsOctober 202612 min read

Design a Metrics and Monitoring System: A Prometheus Pipeline

How to design a metrics and monitoring system end to end: instrumentation, pull versus push, time-series storage maths, cardinality, retention and alerting.

Showing 127–132 of 818 posts

Explore More

Projects

See the projects I've built

Experience

My professional career

Certifications

Professional certifications