gitpulse

vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

97,101 星标24,929 复刻PythonApache-2.0推送于 2026-11-17

在 GitHub 上查看 →

星标动能

今日+76 (+0.1%)
本周+428 (+0.4%)
本月+3,063 (+3.3%)

主题

gptllmpytorchmodel-servingtransformerllm-servinginferencellamaamdcudatpudeepseekqwenblackwelldeepseek-v3gpt-osskimimoeopenaiqwen3