Basu Jindal

nanochat. The best ChatGPT that $100 can buy.

flash-attention. Fast and memory-efficient exact attention

whatsapp-mcp. WhatsApp MCP server

cutlass. CUDA Templates and Python DSLs for High-Performance Linear Algebra

fast.cu. Fastest kernels written from scratch

DeepGEMM. DeepGEMM: clean and efficient BLAS kernel library on GPU

CutlassAcademy. A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS

distrifuser. [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

searchthearxiv. The code powering searchthearxiv.com, a simple semantic search engine for more than 500,000 ML papers on arXiv.

intel-undervolt. Intel CPU undervolting and throttling configuration tool

linux-intel-undervolt. Guide to linux undervolting for Haswell and never Intel CPUs

mdlm. [NeurIPS 2024] Simple and Effective Masked Diffusion Language Model

hackerverse. Exploring Hacker News by mapping and analyzing 40 million posts and comments for fun

penzai. A JAX research toolkit for building, editing, and visualizing neural networks.

llm.c. LLM training in simple, raw C/CUDA

torch-int. This repository contains integer operators on GPUs for PyTorch.

lightning-thunder. PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily write your own.

marlin. FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

grok-1. Grok open release

flash-attention-minimal. Flash Attention in ~100 lines of CUDA (forward pass only)

stable-diffusion. Optimized Stable Diffusion modified to run on lower GPU VRAM

big-AGI. AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.

DRUGS. Stop messing around with finicky sampling parameters and just use DRµGS!

Stirling-PDF. #1 PDF Application on GitHub that lets you edit PDFs on any device anywhere

Gooey. Turn (almost) any Python command line program into a full GUI application with one line

zen-desktop. Ad-blocker and privacy guard for Windows, macOS and Linux.

llamafile. Distribute and run LLMs with a single file.

sshx. Fast, collaborative live terminal sharing over the web

scrcpy. Display and control your Android device

fast-stable-diffusion. fast-stable-diffusion + DreamBooth

shadow. Shadow is a new novel web engine made (almost) entirely in JS from scratch

neurips_llm_efficiency_challenge. NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day

datablations. Scaling Data-Constrained Language Models

hosts. 🔒 Consolidating and extending hosts files from several well-curated sources. Optionally pick extensions for porn, social media, and other categories.

cowrie. Cowrie SSH/Telnet Honeypot https://docs.cowrie.org/

LLaVA-Med. Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

InstagramUnfollowers. Check if people follows you back on Instagram.

progress. Linux tool to show progress for cp, mv, dd, ... (formerly known as cv)

croc. Easily and securely send things from one computer to another :crocodile: :package:

alpaca-lora. Instruct-tune LLaMA on consumer hardware

my_notes. My small cheatsheets for data science, ML, computer science and more.

whisper.cpp. Port of OpenAI's Whisper model in C/C++

TaskMatrix. Python

FlexLLMGen. Running large language models on a single GPU for throughput-oriented scenarios.

awesome-ml-model-compression. Awesome machine learning model compression research papers, quantization, tools, and learning material.

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

vramfs. VRAM based file system for Linux

shell_gpt. A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.

Conference-Acceptance-Rate. Acceptance rates for the major AI conferences

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

ttyd. Share your terminal over the web

petals. 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

openOutpaint-webUI-extension. direct A1111 webUI extension for openOutpaint

apk.sh. Makes reverse engineering Android apps easier, automating repetitive tasks like pulling, decoding, rebuilding and patching an APK.

lovely-tensors. Tensors, for human consumption

serial-terminal. Demo application for the Web Serial API.

CVE-2022-2588. exploit for CVE-2022-2588

ml-surveys. 📋 Survey papers summarizing advances in deep learning, NLP, CV, graphs, reinforcement learning, recommendations, graphs, etc.

linux-wifi-hotspot. Feature-rich wifi hotspot creator for Linux which provides both GUI and command-line interface. It is also able to create a hotspot using the same wifi card which is connected to an AP already ( Similar to Windows 10).

Summer2026-Internships. Summer 2026 software engineering, data science, AI, quant, product management, and hardware internship postings. Updated daily by Simplify and Pitt CSC.

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

awesome-tips.

the-art-of-command-line. Master the command line, in one page

stable-diffusion. A latent text-to-image diffusion model

awesome-ml-internships. List of companies offering Machine learning and Data Science internships

build-your-own-x. Master programming by recreating your favorite technologies from scratch.

pyctcdecode. A fast and lightweight python-based CTC beam search decoder for speech recognition.

BITB. Browser In The Browser (BITB) Templates

Practical_RL. A course in reinforcement learning in the wild

curl-impersonate. curl-impersonate: A special build of curl that can impersonate Chrome & Firefox

mmd.js. mmd.js is an itsy bitsy standalone minimalist Markdown parser written in JavaScript.

gans-awesome-applications. Curated list of awesome GAN applications and demo

PiFmRds. FM-RDS transmitter using the Raspberry Pi's PWM

linux. Linux kernel source tree

staticFormEmails. how to put forms which send emails onto static sites

iBot-Hexapod_RL. Files Containing Hexapod for Simulation

PPO-PyTorch. Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch