1,802 dependents
| Package | Description | Downloads/month |
|---|---|---|
| SGLang is a high-performance serving framework for large language models and mul... | 287.7M | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 9.4M | |
| FlashInfer: Kernel Library for LLM Serving | 4M | |
| 3M | ||
| State-of-the-art speaker diarization toolkit | 2.2M | |
| Give your project support for a variety of PyTorch model architectures, includin... | 1.8M | |
| Vector (and Scalar) Quantization, in Pytorch | 1.7M | |
| Fast and memory-efficient exact attention | 1.4M | |
| A concise but complete full-attention transformer with a set of promising experi... | 1.4M | |
| DeepSpeed is a deep learning optimization library that makes distributed trainin... | 1.3M | |
| Open WebUI | 1.3M | |
| Chronos: Pretrained Models for Time Series Forecasting | 928K | |
| Fast and Accurate ML in 3 Lines of Code | 914K | |
| OCR, layout analysis, reading order, table recognition in 90+ languages | 797K | |
| Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch | 606K | |
| FlashAttention-3 forward | 521K | |
| 🔎 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS,... | 487K | |
| A framework for efficient model inference with omni-modality models | 477K | |
| An implementation of local windowed attention for language modeling | 461K | |
| 🚀 Efficient implementations for emerging model architectures | 415K | |
| Some utility functions to help myself (and perhaps others) go faster with ML/AI ... | 408K | |
| Fast and memory-efficient exact attention | 406K | |
| Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python p... | 364K | |
| Attempt to make multiple residual streams from Bytedance's Hyper-Connections pap... | 357K | |
| Auxillary models for controlnet | 354K | |
| Implements extra model architectures for spandrel | 327K | |
| cortical is the framework for building fabric architectures | 325K | |
| 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and p... | 292K | |
| Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) propos... | 291K | |
| TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial ... | 232K | |
| Qwen-TTS python package | 209K | |
| 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning | 204K | |
| 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and p... | 202K | |
| ⚡ TabPFN: Foundation Model for Tabular Data ⚡ | 194K | |
| Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, ... | 171K | |
| Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a ... | 167K | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 143K | |
| The official Pytorch implementation of Fast Context-based Pitch Estimation (FCPE... | 140K | |
| Lora beYond Conventional methods, Other Rank adaptation Implementations for Stab... | 139K | |
| A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs). | 132K | |
| Mamba SSM architecture | 125K | |
| Axial Positional Embedding | 125K | |
| A toolset for compressing, deploying and serving LLM | 123K | |
| VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice D... | 122K | |
| A Python toolkit/library for reality-centric machine/deep learning & data mining... | 122K | |
| Audiocraft is a library for audio processing and generation with deep learning. ... | 122K | |
| Generative models for conditional audio generation | 118K | |
| The new inference engine for Computer Vision models | 117K | |
| Implementation of the conditionally routed attention in the CoLT5 architecture, ... | 110K | |
| Implementation of Vision Transformer, a simple way to achieve SOTA in vision cla... | 109K |
