vLLM
@vllm_project
A high-throughput and memory-efficient inference and serving engine for LLMs. Join to discuss together with the community!
๊ฐ์
March 2024
36 ํ๋ก์ ์ค 38.7K ํฌ
Congrats to @AntLingAGI on Ring-2.6-1T going open! ๐
The thinking sibling of Ling-2.6-1T โ trillion-scale, built for agent execution and complex reasoning.
Day-0 vLLM support is ready.
๐ค
๋ ๋ณด๊ธฐ
