Harsha Mangena

@harshamangena

A passionate backend developer

EarthJoined June 2022

About

Graduated in 2021. Later worked as an Associate for 6-months in MNC. Later joined the fellowship at BootCamp in backend development. Currently preparing for interviews.

Available for

Preparing for interviews and searching for opportunities.

Harsha Mangena's blogs

Untitled Publicationharshamangena.hashnode.dev42 posts

Code with Harshacodewithyou.hashnode.dev6 posts

The Machine Learning Dude'smachinelearningdudes.hashnode.dev1 post

Articles Comments

Recently published

HMHarsha Mangenaharshamangena.hashnode.devApr 30 · 19 min read

RouteKV Compiler: The Brain That Decides Where Your LLM's Memory Lives

Imagine you're running a massive LLM in production think 128K context windows, thousands of concurrent users, all hammering your GPU cluster. At some point, you notice something weird: your GPUs aren'

0

HMHarsha Mangenaharshamangena.hashnode.devMar 27, 2025 · 6 min read

AI CLI in GO

Workflow with CodeAI CLI CodeAI CLI is a command-line tool designed to empower developers by integrating artificial intelligence capabilities directly into their development environment. Leveraging local large language models (LLMs) through the Ollam...

0

HMHarsha Mangenaharshamangena.hashnode.devMar 6, 2025 · 8 min read

Micro LLMs: Fine-Tuning for Specific Tasks

Introduction Hey there! If you've been following the AI space lately, you've probably heard about Large Language Models (LLMs) like ChatGPT, Claude, or LLaMA. These AI marvels can write essays, answer questions, and even create code. But there's a ne...

0

HMHarsha Mangenaharshamangena.hashnode.devFeb 5, 2025 · 3 min read

Tools for LLM Tuning

Training large language models (LLMs) can feel like trying to tame a dragon: powerful, resource-hungry, and intimidating. But with the right tools, even beginners can achieve impressive results. In this guide, we’ll explore three popular frameworks—U...

0

HMHarsha Mangenaharshamangena.hashnode.devFeb 3, 2025 · 6 min read

Advanced Adapter Merging Strategies in LLMs

In the rapidly evolving landscape of Large Language Models (LLMs), the ability to efficiently customize and adapt these models for specific tasks has become increasingly crucial. This comprehensive guide explores two sophisticated adapter merging str...

0

Harsha Mangena

About

Available for

Harsha Mangena's blogs

Recently published

RouteKV Compiler: The Brain That Decides Where Your LLM's Memory Lives

AI CLI in GO

Micro LLMs: Fine-Tuning for Specific Tasks

Tools for LLM Tuning

Advanced Adapter Merging Strategies in LLMs

Search Hashnode

Harsha Mangena

About

Available for

Harsha Mangena's blogs

Recently published

RouteKV Compiler: The Brain That Decides Where Your LLM's Memory Lives

AI CLI in GO

Micro LLMs: Fine-Tuning for Specific Tasks

Tools for LLM Tuning

Advanced Adapter Merging Strategies in LLMs