260 dependents
| Package | Description | Downloads/month |
|---|---|---|
| SGLang is a high-performance serving framework for large language models and mul... | 287.7M | |
| Provide Python access to the NVML library for GPU diagnostics | 4.8M | |
| FlashInfer: Kernel Library for LLM Serving | 4M | |
| Turn any computer or edge device into a command center for your computer vision ... | 1.1M | |
| Turn any computer or edge device into a command center for your computer vision ... | 836K | |
| An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for G... | 418K | |
| A unified library of SOTA model optimization techniques like quantization, pruni... | 376K | |
| Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Py... | 351K | |
| AIPerf is a package for performance testing of AI models | 285K | |
| Transformers-compatible library for applying various compression algorithms to L... | 285K | |
| Utilities for Dask and CUDA interactions | 260K | |
| Track emissions from Compute and recommend ways to reduce their impact on the en... | 205K | |
| The easiest way to serve AI apps and models - Build Model Inference APIs, Job qu... | 198K | |
| ⚡️SwanLab - an open-source, modern-design AI training tracking and visualization... | 183K | |
| Shared Python utilities used across the TabPFN ecosystem — data helpers, regress... | 180K | |
| cuDF - GPU DataFrame Library | 120K | |
| Turn any computer or edge device into a command center for your computer vision ... | 119K | |
| Python Bindings for the Unified Communication X library (UCX) | 116K | |
| cuEquivariance is a math library that is a collective of low-level primitives an... | 111K | |
| NVIDIA Resiliency Extension is a python package for framework developers and use... | 82K | |
| Swap GPT for any LLM by changing a single line of code. Xinference lets you run ... | 43K | |
| An open source AutoML toolkit for automate machine learning lifecycle, including... | 34K | |
| OpenRunner SDK - W&B-compatible ML experiment tracking client | 26K | |
| cuDF - GPU DataFrame Library | 24K | |
| SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics si... | 22K | |
| Go ahead and axolotl questions | 20K | |
| Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API e... | 18K | |
| cuEquivariance is a math library that is a collective of low-level primitives an... | 16K | |
| TensorRT LLM provides users with an easy-to-use Python API to define Large Langu... | 16K | |
| 🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Di... | 15K | |
| The main vantage6 repository: code for the central server, nodes, CLI and Python... | 13K | |
| NeuralBroker — A VRAM-aware LLM router. Daemon polls GPU every 500ms, routes req... | 13K | |
| [ICML 2026] effGen: Enabling Small Language Models as Capable Autonomous Agents | 10K | |
| PixlStash is a Python-based image management, tagging and editing web app levera... | 10K | |
| Nsight Python is a Python kernel profiling interface based on NVIDIA Nsight Tool... | 10K | |
| Turn any computer or edge device into a command center for your computer vision ... | 9K | |
| A package for LISA Data Analysis | 9K | |
| Train models with self-supervised learning in a single command | 8K | |
| SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics si... | 8K | |
| Provides a unified interface to detect GPU resources and manages GPU workloads. | 8K | |
| The Attestation SDK provides developers with a easy to use APIs for implementing... | 8K | |
| GPU process monitor — see who's using the GPU with full process details | 7K | |
| Turn any computer or edge device into a command center for your computer vision ... | 7K | |
| A tool to find homologous interactions and speed up AlphaFold-based structural m... | 7K | |
| 🧪 Reusable nox recipes for uv-managed environments, pytest sessions, dependency-... | 6K | |
| Utilities for deep learning on multimodal data. | 6K | |
| Protein design | 6K | |
| A package to hold various functions to support training of ML models. | 5K | |
| ✅A Lightweight Video RAG Framework for Multimodal Reasoning | 5K | |
| Terminal dashboard for NVIDIA GPUs, system CPU/memory, and processes — clickable... | 5K |
