- Seattle, Washington
- angadjosan@outlook.com
- in/angad-singh-josan
- https://logiclounge.beehiiv.com/
Stars
Basic machine learning algorithms, written from scratch in C++ with Python bindings for learning purposes.
OSS-Fuzz - continuous fuzzing for open source software.
Leaderboard and Solutions for Logic Lounge problems.
aider is AI pair programming in your terminal
A high-throughput and memory-efficient inference and serving engine for LLMs
【CVPR'2023】Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
🦔 PostHog provides open-source web & product analytics, session recording, feature flagging and A/B testing that you can self-host. Get started - free.
Efficient Triton Kernels for LLM Training
Curated list of internships/externships/fellowships exclusive for CS freshman and sophomore (updated for 2025!)
Python implementation of my paper "Age Adaptive Language Competition in Social Networks"
I made this project while interning at Google Research. It is the first ever python implementation of an Einstein Tile pattern generator. This tiling was discovered in 2022 and provides infinite ap…
schej helps you quickly find the best time for your group to meet. It's like When2meet with Google Calendar integration!
Semantic Occupancy 3D Plotter. This is the plotter made by the SOccDPT project to create fancy 3D visuals. You can use this for your own AV or Robotics visualization!
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
[ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
The Open Source DocuSign Alternative.
🧮 A collection of resources to learn mathematics for machine learning
The simplest, fastest repository for training/finetuning medium-sized GPTs.
llama3 implementation one matrix multiplication at a time
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.