164 dependents
| Package | Description | Downloads/month |
|---|---|---|
| A high-throughput and memory-efficient inference and serving engine for LLMs | 9.4M | |
| Be a master builder of databases of material properties. Avoid the Kragle. | 888K | |
| The simplest way to serve AI/ML models in production | 632K | |
| A Python utility library with logging and path management | 612K | |
| Python SDK for the Plato API | 408K | |
| Self describing hashes - for future proofing | 150K | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 143K | |
| Supercharge Your LLM with the Fastest KV Cache Layer | 120K | |
| ONEX Core Framework - Base classes and essential implementations for the ONEX ec... | 98K | |
| Invoke is a leading creative engine for Stable Diffusion models, empowering prof... | 77K | |
| Core of vaex | 64K | |
| Wheels & Docker images for running vLLM on CPU-only systems, optimized for diffe... | 31K | |
| Supply chain security for ML | 25K | |
| The Lightning Logger of the Lightning.AI Platform | 22K | |
| TensorRT LLM provides users with an easy-to-use Python API to define Large Langu... | 16K | |
| Asynchronous Component Base | 15K | |
| Python SDK for Galileo's NLP and CV Studio. | 11K | |
| Unlimited cloud storage using Telegram MTProto. No local DB - everything on Tele... | 10K | |
| #1 Website in the Worlds | 9K | |
| Jolt is a task execution tool designed for software development tasks. It can bu... | 8K | |
| Python library to interact with the Astreum blockchain and its virtual machine. | 8K | |
| Unofficial python bindings for llm-rs. 🐍❤️🦀 | 8K | |
| Supply chain security for ML | 8K | |
| Large-scale LLM inference engine | 7K | |
| 7K | ||
| ISCC - Codec & Algorithms | 6K | |
| Nexus, the shared heartbeat where every agent and human connect, collaborate, an... | 6K | |
| A library used to build custom functions in Cozy Creator's serverless function p... | 6K | |
| A framework for reproducible prospecting of CUDA applications. | 6K | |
| Shared Python toolkit for OuEstCharlie agents | 6K | |
| Python Hierarchical Concurrency Rich Context Asynchronous IO. | 5K | |
| Dropbox-like file server with modern web interface | 5K | |
| Key Event Receipt Infrastructure - the spec and implementation of the KERI proto... | 5K | |
| Project AIR: forensic reconstruction and incident response for AI agents. Signed... | 4K | |
| SDK for creating ISCCs (International Standard Content Codes) | 3K | |
| A bunch of utilities aggregated over time | 3K | |
| A perfect AI powered RAG for document query and summary. Supports ~all LLM and ~... | 3K | |
| Unified filesystem abstraction for cloud storage — mount S3, GCS, and local stor... | 3K | |
| Wheels & Docker images for running vLLM on CPU-only systems, optimized for diffe... | 3K | |
| Production-ready caching for Python with intelligent reliability features and Ru... | 3K | |
| Canonicalization, fingerprinting, and change detection for GTFS Schedule feeds. | 3K | |
| Semantic code search for AI agents — 166+ languages, hybrid search, works offlin... | 3K | |
| GoFigr client library | 3K | |
| vLLM CPU inference engine (AVX512 + VNNI optimized) | 3K | |
| Lightweight MCP server for semantic file caching with 80%+ token reduction | 3K | |
| Wheels & Docker images for running vLLM on CPU-only systems, optimized for diffe... | 3K | |
| ComfyGit monorepo containing the core libraries, CLI tools, and deployment utili... | 3K | |
| MSL memory dump tool with pluggable debugger backends (Frida, GDB, LLDB) | 2K | |
| vLLM CPU inference engine (AVX512 optimized) | 2K | |
| ComfyUI inference engine as a standalone Python library (no server, no UI). | 2K |
