Auto-tuning for vllm. Getting the best performance out of your LLM deployment (vllm+guidellm+optuna)

A hardware-aware guide to data structures for system software engineers.

Competitor Analysis PoC Helm Charts and Guide

A collection of prompts, system prompts and LLM instructions

Zork I (Microcomputer Version) by Infocom

AI Bank Statement Document Automation By LLM model and Personal Finanical Analysis

Red Hat OpenShift AI Roadshow v2

Hierarchical Reasoning Model Official Release

Open Source framework for voice and multimodal conversational AI

vLLM plugin for RBLN NPU

This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for re…

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

Synthetic Data Generation Toolkit for LLMs

A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

Various Telco AI Usecases & Experiments

LLM inference in C/C++

Fully open reproduction of DeepSeek-R1

Resources of our paper "FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces". New versions in the making!

The LLM Evaluation Framework

Attempt to create an Open Source Privacy Focused Rewind.ai Alternative that is a POD (Personal Online Datastore)

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

A Lightweight Recommendation System

Testing baseline LLMs performance across various models

AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code

A generative world for general-purpose robotics & embodied AI learning.