- New Delhi, India
- https://rootavish.github.io
Highlights
Stars
Fastest LLM gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
The Google Scholar PDF Reader browser extension, now with annotations!
DeepEP: an efficient expert-parallel communication library
FlashMLA: Efficient Multi-head Latent Attention Kernels
Nodes for image juxtaposition for Flux in ComfyUI
Entropy Based Sampling and Parallel CoT Decoding
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
A simple and efficient tool to parallelize Pandas operations on all available CPUs
A high-throughput and memory-efficient inference and serving engine for LLMs
Fast and memory-efficient exact attention
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
⬆️ ☠️ 🔥 Automatic Linux privesc via exploitation of low-hanging fruit e.g. gtfobins, pwnkit, dirty pipe, +w docker.sock
Download market data from Yahoo! Finance's API
Realtime Data From National Stock Exchange (India)
Real-time microphone noise suppression on Linux.
😤 Awesome Identity is a single-page Hugo theme to introduce yourself.
🚀 Awesome list of open source applications for macOS. https://t.me/s/opensourcemacosapps
A small course on exploiting and defending neural networks
⚡ A Fast, Extensible Progress Bar for Python and CLI
A simple, battle-tested and generic set type for the Go language. Trusted by GoogleCloudPlatform, Docker, 1Password, Ethereum and Hashicorp.
Production-Grade Container Scheduling and Management
A curated list of articles complaining that go (golang) isn't good enough