Stars
PyTorch implementation of LEARNING LATENT PERMUTATIONS WITH GUMBEL-SINKHORN NETWORKS
Ailoy is a developer-friendly library that simplifies building and deploying AI agents and LLM-based applications.
A somewhat minimal but structured jumping-off point for Neovim with Lazy.nvim
A final sanity checklist to help your CS paper get accepted, not desk rejected.
Tile primitives for speedy kernels
A community-maintained Python framework for creating mathematical animations.
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
This repo is an implementation of PyTorch version YOLOV Series
Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.
[IEEE Access 2025] One-Hot Multi-Level Leaky Integrate-and-Fire Spiking Neural Networks for Enhanced Accuracy-Latency Tradeoff
A minimalist and elegant presentation theme for Quarto Reveal.js
Efficient kernel for RMS normalization with fused operations, includes both forward and backward passes, compatibility with PyTorch.
Fast Hadamard transform in CUDA, with a PyTorch interface
Causal depthwise conv1d in CUDA, with a PyTorch interface
Collections of awesome neovim plugins.
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.
Pre-built components and code samples to help you build and deploy production-grade AI applications with the OpenVINO™ Toolkit from Intel
Group elastic net implementation in PyTorch.
Awesome LLM pruning papers all-in-one repository with integrating all useful resources and insights.
Classical equations and diagrams in machine learning
Machine Learning and Computer Vision Engineer - Technical Interview Questions
[NeurIPS 2024] BLAST: Block Level Adaptive Structured Matrix for Efficient Deep Neural Network Inference
Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation (ICML'24 Oral)
Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".
An official PyTorch implementation of "Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks," ICLR 2024.