1,008 dependents
| Package | Description | Downloads/month |
|---|---|---|
| SGLang is a high-performance serving framework for large language models and mul... | 287.7M | |
| IPython Kernel for Jupyter | 78.2M | |
| Jupyter protocol client APIs | 78.2M | |
| The backend—i.e. core services, APIs, and REST endpoints—to Jupyter web applicat... | 53.8M | |
| Jupyter terminal console | 18.6M | |
| Write scalable load tests in plain Python 🚗💨 | 13.6M | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 9.4M | |
| Our library for RL environments + evals | 2.3M | |
| A reactive notebook for Python — run reproducible experiments, query with SQL, e... | 2.2M | |
| Building blocks for scientific data pipelines | 745K | |
| A framework for efficient model inference with omni-modality models | 477K | |
| Wearable cognitive assistance using cloudlets | 324K | |
| Interactive Parallel Computing with IPython | 302K | |
| Petastorm library enables single machine or distributed training and evaluation ... | 287K | |
| AIPerf is a package for performance testing of AI models | 285K | |
| A Process & Socket Manager built with zmq | 271K | |
| The Scientific Python Development Environment | 167K | |
| Jupyter Kernels for the Spyder console | 148K | |
| A Process & Socket Manager built with zmq | 145K | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 143K | |
| A toolset for compressing, deploying and serving LLM | 123K | |
| Supercharge Your LLM with the Fastest KV Cache Layer | 120K | |
| Jupyter Notebook Extension for monitoring your own Resource Usage | 111K | |
| Python client for Kinetica DB | 110K | |
| Real-time avatar engine — 100+ FPS on CPU. Generate lip-synced video, stream liv... | 104K | |
| FlowKit: Flowminder CDR analytics toolkit | 98K | |
| A python implementation of the aphrodite's specification, heavily based on WCMF | 97K | |
| The recursive internet scanner for hackers. 🧡 | 93K | |
| ERT - Ensemble based Reservoir Tool - is designed for running ensembles of dynam... | 87K | |
| Determined AI: The fastest and easiest way to build deep learning models. | 69K | |
| Efficient, lightweight and reliable distributed computation engine | 63K | |
| Parsl - a Python parallel scripting library | 57K | |
| PyTorch Single Controller | 47K | |
| PyTest Salt Factories Plugin | 46K | |
| F´ Python Ground Data System (GDS). | 46K | |
| 基于Python的开源量化交易平台开发框架 | 40K | |
| DeGirum AI Inference Software Package | 39K | |
| Base OAREPO package freezeing versions of libraries | 39K | |
| A minimal Python framework for building custom AI inference servers with full co... | 37K | |
| Asynchronous API for ZMQ using AnyIO. | 36K | |
| Wheels & Docker images for running vLLM on CPU-only systems, optimized for diffe... | 31K | |
| zerorpc for python | 31K | |
| Open source dataflow engine in Django | 31K | |
| Cylc: a general purpose workflow engine with a gift for cycling | 28K | |
| A framework for researchers | 26K | |
| Backend.AI is a streamlined, container-based computing cluster platform that hos... | 26K | |
| A simple AI/ML modeling tool, Link™ ensures a smoother flow and a better experie... | 25K | |
| A Reference Open Source Controller for Wind Turbines | 25K | |
| 24K | ||
| Perform data science on data that remains in someone else's server | 23K |
