GitHub439github.com
vllm-project/vllm
by vllm-project首次上榜 2026-10-20
摘要
vLLM 是一个面向大语言模型的高吞吐、显存高效的推理与服务引擎，最初在伯克利 Sky Computing Lab 开发，README 中附有 arXiv 论文、文档站和开发者 Slack 等入口。它适合需要自建 LLM 在线服务、又对吞吐量和显存占用敏感的团队评估或直接部署。
近 7 天热度
10-2010-21
相关推荐
[分享创造] 测了 1000 个中文大站的 llms.txt，只有 30 个放了真正的文件
alibaba/open-code-review
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
DeepInfer: High-performance inference framework for DeepSeek models
Comfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.