-
AMD
- United States
Highlights
- Pro
Starred repositories
Unsupervised text tokenizer for Neural Network-based text generation.
A curated list of awesome parallel computing resources
Collective communications library with various primitives for multi-machine training.
General-purpose web UI for Kubernetes clusters
HIP: C++ Heterogeneous-Compute Interface for Portability
A React Framework for building internal tools, admin panels, dashboards & B2B apps with unmatched flexibility.
Development repository for the Triton language and compiler
You like pytorch? You like micrograd? You love tinygrad! ❤️
Dataframes powered by a multithreaded, vectorized query engine, written in Rust
A light-weight, flexible, and expressive statistical data testing library
Vulkan/CUDA/HIP/OpenCL/Level Zero/Metal Fast Fourier Transform library
Meta-Transformer for Unified Multimodal Learning
Always know what to expect from your data.
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)
Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)
Summary of related papers on visual attention. Related code will be released based on Jittor gradually.
Awesome-LLM: a curated list of Large Language Model
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
ImageBind One Embedding Space to Bind Them All
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.