vllm-project / vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
维护停滞 Apache 2.0 Python Star
95.6k 24.0k 32 分钟前
CIPyPI
gpt llm pytorch model-serving transformer llm-serving inference llama amd cuda tpu deepseek qwen blackwell deepseek-v3 gpt-oss kimi moe openai qwen3
星标趋势
数据积累中，暂无足够数据生成趋势图
AI 分析
项目摘要
vllm-project/vllm: A high-throughput and memory-efficient inference and serving engine for LLMs
为什么值得关注
High popularity with 95,606 stars, active contributor community (3014 contributors), frequent releases.
优势
- Large and active community
- Continuous integration configured
- Test suite present
局限性
- Limited documentation
分析模型：fallback | 分析时间：刚刚