vLLM-Omni首日支持MiniMax H3-Image
vLLM博客称，vLLM-Omni现已支持开放权重的MiniMax H3-Image，该模型可进行原生高分辨率文生图和图像编辑。报告团队在四块NVIDIA Vera Rubin GPU上的短提示词服务基准中测得，原生4096×4096生成的中位耗时为0.87秒。另一些测试显示，四块GB300 GPU完成4K生成平均耗时1.48秒，带一张参考图的4K编辑平均耗时1.77秒；Rubin上的详细提示词测试平均耗时为1.09秒。相关实现和部署配方还覆盖AMD Instinct、Intel Arc Pro、Huawei Ascend和Moore Threads硬件，但各平台的验证配置和结果有所不同。
此次发布提供了H3-Image的首日服务实现、部署配方以及针对不同硬件平台的验证结果。
We brought MiniMax H3-Image to NVIDIA Vera Rubin with vLLM-Omni. On four GPUs, native 4096×4096 generation reaches 0.87 seconds median in our short-prompt serving benchmark. A separate throughput configuration delivers 6,115 images/hour, projecting to 146,755 images/day.
At USD 0.06879 per image, using MiniMax's official Standard 4K API pricing example before launch discounts as an assumed sale price, peak throughput projects to USD 105.16/GPU/hour in gross revenue at full billable utilization, or USD 78.87/GPU/hour at 75%. These estimates are before operating costs; the daily capacity is an extrapolation of the measured rate.
H3-Image is an open-weight model for text-to-image generation and image editing. One checkpoint handles both tasks in six sampling steps, generates native high-resolution images without an upscaler, and supports up to 16 reference images.
We bring H3-Image to consumer and data-center GPUs, spanning NVIDIA, AMD, Intel and Moore Threads (MUSA), as well as Huawei Ascend NPUs.
#MiniMax#H3-Image#vLLM-Omni#NVIDIA Vera Rubin#NVIDIA GB300#NVIDIA H200#NVIDIA RTX 5090#AMD Instinct#Intel Arc Pro#Huawei Ascend#Moore Threads MUSA#OpenDirector