Differentiable architecture search for convolutional and recurrent networks
- deep-learning
- automl
- image-classification
- language-modeling
108,094 visible repositories in the index
145–168 of 687 · Most stars
Differentiable architecture search for convolutional and recurrent networks
Learning in infinite dimension with neural operators.
State-of-the-art LLM compression, built for production inference with vLLM
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
Deep neural networks for voice conversion (voice style transfer) in Tensorflow
The repository host gives no description.
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
TranslatedThe complete AI Agent interview guide: from zero to Offer, including 200+ interview questions, enterprise-level projects (Python/Java/Go), resume templates, STAR interview scripts, and Doraemon comic illustrations
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
CnOCR: Awesome Chinese/English OCR Python toolkits based on PyTorch. It comes with 20+ well-trained models for different application scenarios and can be used directly after installation. 【基于 PyTorch/MXNet 的中文/英文 OCR Python 包。】
The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the model.
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Hummingbird compiles trained ML models into tensor computation for faster inference.
PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.
A library for transfer learning by reusing parts of TensorFlow models.
Open-source inference server and production cluster for all the models your agent needs.
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools
Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included.