---
title: "Akshay Suryawanshi (@akshaysuryawanshi) | Hashnode"
description: "Sharing thoughts about my learning of Inference Engineering. Read the latest articles by Akshay Suryawanshi on Hashnode."
url: "https://hashnode.com/@akshaysuryawanshi"
---

@akshaysuryawanshi

# Akshay Suryawanshi

@akshaysuryawanshi · Ottawa, Canada · Joined October 2026

Sharing thoughts about my learning of Inference Engineering.

### [From Replicas to FP8: My First vLLM Performance Investigation](https://akshaysuryawanshi.hashnode.dev/from-replicas-to-fp8-my-first-vllm-performance-investigation?utm_source=hashnode&utm_medium=feed)

Testing vLLM replicas, NVIDIA MPS, and FP8 KV cache and attention on one laptop GPU, measuring throughput, latency, goodput, and answer quality.

10 min read · [akshaysuryawanshi.hashnode.dev](https://akshaysuryawanshi.hashnode.dev/from-replicas-to-fp8-my-first-vllm-performance-investigation?utm_source=hashnode&utm_medium=feed)

[Oct 16](https://hashnode.com/posts/from-replicas-to-fp8-my-first-vllm-performance-investigation/6ad2ae0da305ffe6691825e0)

### [A Database Engineer’s First Look at LLM Inference.](https://akshaysuryawanshi.hashnode.dev/first-look-at-llm-inference?utm_source=hashnode&utm_medium=feed)

A database engineer's first LLM inference experiment: running Qwen3-0.6B with vLLM on an 8GB laptop GPU and making sense of latency and throughput.

11 min read · [akshaysuryawanshi.hashnode.dev](https://akshaysuryawanshi.hashnode.dev/first-look-at-llm-inference?utm_source=hashnode&utm_medium=feed)

[Oct 14](https://hashnode.com/posts/first-look-at-llm-inference/6acf9533a2ed742f7adc8453)