gitpulse

vllm-project/vllm

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

97,025 stars24,897 forksPythonApache-2.0pushed 2026-11-16

View on GitHub →

Star momentum

Today+70 (+0.1%)
This week+427 (+0.4%)
This month+3,055 (+3.3%)

Topics

gptllmpytorchmodel-servingtransformerllm-servinginferencellamaamdcudatpudeepseekqwenblackwelldeepseek-v3gpt-osskimimoeopenaiqwen3