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 50.2K ํฌ
Qwen-Image-2.1 from @Alibaba_Qwen has day-0 support in vLLM-Omni. ๐
Generate, edit, and create transparent images with one model: a 7.1B DiT paired with Qwen3-VL-8B.
Setup and supported combinations ๐
๋ ๋ณด๊ธฐ
