Vishnu's engineering notebook

Infrastructure. Local AI. Learning by doing.

I’m Vishnu, a platform engineer in Singapore. These are my notes from building and breaking things: Kubernetes clusters, GPU nodes, and models running on my own hardware. Most posts include the exact commands I ran. More about me →

Read the latest Search /
Singapore · UTC+8
Jump to

$ ls -t ./notes

Latest notes.

All notes
Pixel art of three llama portraits rendered at progressively coarser precision beside a compact GPU

LLM Quantization, Simply: FP16, 8-bit, 4-bit, and What Q4_K_M Means

A simple, diagram-first guide to LLM quantization: what rounding a weight actually does, how much memory each bit width saves, how to read names like Q4_K_M, AWQ, and FP8, and a toy script that shows where quality falls off.

Pixel art of a token bucket metering small requests through a shield-shaped gateway while blocking an oversized request

Rate Limiting LLM APIs: Count Tokens, Not Requests

A diagram-first guide to token budgets, fair admission, and load shedding for shared LLM APIs, with a runnable Python simulation.

Pixel art comparison showing a glowing branching Radix tree with structured bracket gates on the left and a GPU processor core packing memory pages into parallel token streams on the right

SGLang vs. vLLM: RadixAttention, Structured Outputs, and When to Pick Which

A simple, diagram-first comparison of SGLang and vLLM: how RadixAttention works, how jump-forward decoding speeds up JSON outputs, how their schedulers compare, and which engine fits your workload.

Pixel art laptop projecting a holographic GPU cluster of amber wireframe cards, with a router tower sending request cubes to them and the brightest path going to the card that holds matching cache cubes

No GPU? Simulate One: vLLM, llm-d, and 16 Fake H100s on a Laptop

A hands-on lab for learning GPU scheduling and LLM routing without a GPU: kind, fake-gpu-operator, llm-d-inference-sim, and the llm-d router, with real screenshots and benchmark numbers.

Pixel art router tower sending glowing requests to GPU racks, with the brightest path going to the rack that already holds matching cache cubes

llm-d, Simply: A Smarter Router for vLLM on Kubernetes

A practical, diagram-first guide to llm-d: why round-robin wastes GPUs, how cache-aware routing works, which well-lit path to start with, and the commands to deploy it.

Pixel art workflow continuing through a durable history server from a crashed worker to a healthy replacement

Temporal Hands-On: Durable Execution on Kubernetes

A hands-on Temporal demo in Python: build a small order workflow, deploy it on Kubernetes, then delete the worker pods mid-execution and watch durable execution resume it.

Pixel art Kubernetes GPU cluster with two servers, cyan GPU interconnects, and a violet network fabric

Kubernetes GPU Platform Engineering: From nvidia-smi to NCCL

A simple, layered guide to GPUs on Kubernetes: GPU Operator, NUMA and PCIe, RDMA, SR-IOV and Multus, NVLink and NCCL, with a troubleshooting question for every layer.

Pixel art laptop with a winged messenger robot exchanging requests with a gem-shaped model chip

Hermes Agent + LM Studio Bionic: Running Gemma 4 Locally

A Windows walkthrough of Hermes Agent connected to LM Studio Bionic with Gemma 4 E4B: local inference, custom endpoint settings, tool use, and the checks that confirm it works.

Pixel art processor turning unstructured documents into parallel decision paths and probability indicators

TypeSafe’s Jev: Early Access to AI Built for Decisions

My early-access look at TypeSafe’s Jev: Noul, Choice, and Score in the playground, the coding-agent skill, and what the performance claims do and do not establish.

Pixel art orchestration hub coordinating three independent Kubernetes server islands

What Is Karmada? Kubernetes Across Clusters, Explained with YAML

Karmada's CNCF graduation, its multi-cluster architecture, and practical YAML for placement, replica splitting, overrides, and failover.