A high-throughput and memory-efficient inference and serving engine for LLMs

Serving llama using llama-cpp-python and kserve

fzf-based test selection with pytest

Simple Deep Learning library in Rust based on ndarray.

A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..

Ongoing research training transformer models at scale

Development repository for the Triton language and compiler

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

Solution for Cornell CS5781 Machine Learning Engineering: MiniTorch https://github.com/minitorch/minitorch

GAN Paint seamlessly combines two non-overlapping patches using a U-Net generator and PatchGAN discriminator for efficient image outpainting and hole filling.

Wise Node Strategy for Rumor Mitigation in Social Networks

Puzzles for exploring transformers

Puzzles for learning Triton

What would you do with 1000 H100s...

Solve puzzles. Learn CUDA.

Implementation of paper Generalised Image Outpainting with UTransformer

Personal Profile

Solve puzzles. Improve your pytorch.

2025 SWE internship & new graduate job list updated daily

2025 AI/ML internship & new graduate job list updated daily

An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.

A collection of full time roles in SWE, Quant, and PM for new grads.

The full minitorch student suite.

Easiest and laziest way for building multi-agent LLMs applications.

.ncm to .mp3 or .flac

This unofficial extension integrates Draw.io (also known as diagrams.net) into VS Code.

The development repository of DeepLink-org/DIOPI