vllm-project

vllm

A high-throughput and memo ry-efficient inference a nd serving engine for LLMs

Trusted Project Python
81.2k stars via trending-python
View on GitHub
Related Python Repos
microsoft/markitdown
Python tool for converting files and office documents to Markdown.
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and he
TauricResearch/TradingAgents
TradingAgents: Multi-Agents LLM Financ ial Trading Framework
harry0703/MoneyPrinterTurbo
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
D4Vinci/Scrapling
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale
← Back to Trending Repos