pytorch

speech-to-text in pytorch

Easy to use pretrained yolov5 models

Unofficial Fastapi implementation of Stable-Diffusion API

Official PyTorch Implementation of "WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models" - ICDAR 2023

Repository for the companion Colab notebook of the Domain-Specific Small Language Models book.

Tiny local text-to-24x24 pixel art model, trained on roughly 200K samples in 30 minutes on an RTX 5090.

Tensorflow, Pytorch, Huggingface Transformer, Fastai, etc. tutorial Colab Notebooks.

Improving Chest X-Ray Report Generation by Leveraging Warm-Starting

A simple service that integrates vLLM with Ray Serve for fast and scalable LLM serving.

Solutions for CS224n (2022)

[ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-Fire mechanism).

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.

🌹 Rose: Range-Of-Slice Equilibration PyTorch optimizer. Stateless optimization through range-normalized gradient updates.

[CVPR 2023, top-10%] Authors official PyTorch implementation of the "Attribute-preserving Face Dataset Anonymization via Latent Code Optimization".

PyTorch-IE: State-of-the-art Information Extraction in PyTorch

Local-first meeting transcription — audio & transcripts never leave your machine. Live captions + upload diarization + voice matching.

LIDIA: Lightweight Learned Image Denoising with Instance Adaptation (NTIRE, 2020)

CUDA and Triton implementations of Flash Attention with SoftmaxN.

[IEEE TCSVT 2023] Official implementation of DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer

⚡️ Implementation of TRON: Transformer Recommender using Optimized Negative-sampling, accepted at ACM RecSys 2023.