Thus it all started!!!

So this new year instead of making all those "Promises" I'm gonna start this new blog. :)
Well The idea has been around for quite some time. But I really didn't had enough time and more importantly the enthusiasm to get through it.
But...Looks like it had to start :D
So here I am.

I'm not quite sure whether I'll be able to maintain this blog as a diary of all my thoughts and ramblings or will this become a junkyard of all my "technical" rants.
But then again...we shall see :)

So next is my first technical post :0

Comments

Racecraft (Project Koru) · Prologue — The Origin Story

Racecraft · Prologue , The Origin Story It Started With a Wine List and a Question About Racing How a happy-hour conversation in the Bay Area turned into a trustable AI race coach , and then into a second version that runs entirely on a phone, on the NPU. This is the prologue to a five-part series. Two years ago(1st November, 2024) I was in the Bay Area for a GDE Summit. If you've never been: it's a couple of days of talks among Google Developer Experts, the kind of people who get unreasonably excited about a new on-device runtime, and then , mercifully , a happy hour where everyone stops performing and just eats. We ended up at a restaurant(Puesto Santa Clara), a long table of GDEs, and I was doing the most important engineering of the evening: trying to decide which wine to order. Across the table was Ajeet Mirwani . I don't even remember how the wine talk turned into racing talk , these things drift , but the moment the word "racing" ...

A Split‑Brain Neuro‑Symbolic Training Method for High‑Velocity Autonomous Coaching from Telemetry

Author: Rabimba Karanjai Scope: Problem statement + data methodology + model training (no deployment discussion) Abstract Real‑time coaching in motorsport is a safety‑critical learning problem : a system must map noisy, high‑frequency telemetry to short, actionable guidance that remains physically consistent and avoids hazardous recommendations . This paper proposes a “Split‑Brain” training formulation that separates (i) a semantic coaching target (what action/critique should be expressed) from (ii) a reflexive interface (how actions are represented as compact, verifiable tokens). The approach trains a Small Language Model (SLM) in the Gemma family [1] using QLoRA fine‑tuning [2] , and introduces a telemetry tokenizer plus teacher‑student synthesis pipeline to generate instruction‑action pairs at scale. Core contribution: a reproducible method to convert “ golden lap ” differential tel...

The Throughput Trap: Benchmarking vLLM on OpenXLA and the Reality of Production LLM Serving

vLLM Systems · DevLab 2026, Deep Dive I was recently invited by the Google TPU team to speak at the OpenXLA Summer DevLab 2026 . This post breaks down our deep-dive evaluation of the matured vLLM + OpenXLA stack, the fundamental engineering mismatches between CUDA and XLA serving paths, and why traditional capacity metrics are lying to you. If you are operating large language models at enterprise scale right now, your platform architecture team is likely staring at a massive infrastructure crossroads: Should we migrate our core serving workloads from GPUs to TPUs? Historically, NVIDIA's CUDA ecosystem was the only serious option for user-facing, low-latency LLM generation. But here in 2026, the economics and infrastructure options have transformed. Google TPUs are highly available, cheaper per chip, and the open-source serving stack built around vLLM and OpenXLA has officially achieved absolute production readiness. Yet, when our infrast...

RK's Rambling

Search This Blog