transformer

[CVPR22] Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch

Julia Implementation of Transformer models

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

Static suckless single batch CUDA-only qwen3-0.6B mini inference engine

[ECCV'2020] STTN: Learning Joint Spatial-Temporal Transformations for Video Inpainting

FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.

A low-latency & high-throughput serving engine for LLMs

A Jest transformer using esbuild

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

The official PyTorch implementation of the paper "SAITS: Self-Attention-based Imputation for Time Series". A fast and state-of-the-art (SOTA) deep-learning neural network model for efficient time-series imputation (impute multivariate incomplete time series containing NaN missing data/values with machine learning). https://arxiv.org/abs/2202.08516

Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon

Transformer Network for Remaining Useful Life Prediction of Lithium-Ion Batteries

MetaFormer Baselines for Vision (TPAMI 2024)