23 个 · LLM 基础设施 · 库
Python SDK、代理服务器（AI Gateway），以 OpenAI（或原生）格式调用 100+ LLM API，支持成本追踪、guardrails、负载均衡和日志记录。[Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
DeepSpeed 是一个深度学习优化库，使分布式训练和推理变得简单、高效且有效。DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
用于快速文本表示与分类的库。Library for fast text representation and classification.
🎨 TypeScript 的穷尽式 Pattern Matching 库，具备智能类型推断。🎨 The exhaustive Pattern Matching library for TypeScript, with smart type inference.
NVIDIA® TensorRT™ 是在 NVIDIA GPU 上进行高性能深度学习推理的 SDK。本仓库包含 TensorRT 的开源组件。NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
用于本地运行 AI 的生产就绪工具包。Production ready toolkit to run AI locally
基于 OpenTelemetry，为你的 GenAI 或 LLM 应用提供开源可观测性。Open-source observability for your GenAI or LLM application, based on OpenTelemetry
面向并利用基础模型的数据处理！🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
🚀 新兴模型架构的高效实现🚀 Efficient implementations for emerging model architectures
通过统一接口对接 LLM 服务商Communicate with an LLM provider using a single interface
轻量、可移植的 LLM 沙箱运行时（代码解释器）Python 库。Lightweight and portable LLM sandbox runtime (code interpreter) Python library.
一款便捷的 lib，用于流畅地与大语言模型（LLM）交互及构建 AI 应用。A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.
🪢 Langfuse API 的自动生成 Java 客户端。🪢 Auto-generated Java Client for Langfuse API
ELM 是将 LLM 应用于能源研究的一系列工具集合。ELM is a collection of utilities to apply Large Language Models (LLMs) to energy research.
AI 原生的结构化数据 wire 格式。在每个前沿模型上实现 100% 理解，比 JSON 减少 50-92% token，跨 17 种格式完成 43B+ 无损往返。Spec v3.4 Stable。The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.4 Stable.
🛠️ 通过 Local-LLM（一款基于 BERT 模型的轻量级 Python 库）在安全环境中实现离线 NLP 工作流，确保可复现性与可靠性。🛠️ Enable offline NLP workflows with Local-LLM, a lightweight Python library for secure environments using the BERT model, ensuring reproducibility and reliability.
DP-ES 官方实现：面向 Prompt 优化的差分隐私进化策略（EMNLP 2026）。Official implementation of DP-ES: Differentially Private Evolution Strategies for Prompt Optimization (EMNLP 2026)
几何有限主义：语言与思维的几何学Geofinitism: The Geometry of Language and Thought
SILVA Networks 是一个 Python 包，提供扩展的深度均衡层、定点求解器、隐式微分、结构化算子、诊断工具以及可复现研究 notebook。SILVA Networks is a Python package for extended deep equilibrium layers, fixed-point solvers, implicit differentiation, structured operators, diagnostics, and reproducible research notebooks.