菜单
SkillsMP 已收集 krafton-ai/vllm-omni 中的 2 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 2 / 2 个已收集 Skill。
Integrate a new text-to-speech model into vLLM-Omni from HuggingFace reference implementation through production-ready serving with streaming and CUDA graph acceleration. Use when adding a new TTS model, wiring stage separation for speech synthesis, enabling…
原文语言：英语
Add a new diffusion model (text-to-image, text-to-video, image-to-video, text-to-audio, image editing) to vLLM-Omni, including Cache-DiT acceleration and parallelism support (TP, SP/USP, CFG-Parallel, HSDP). Use when integrating a new diffusion model, porting…
原文语言：英语