A high-throughput and memory-efficient inference and serving engine for LLMs
其他人工智能更新于 2026-10-25
其他人工智能Apache-2.0
Repository dossier
verl-project/verl-omni
Multimodal RL training framework for diffusion & omni models
Brief / README 摘要
查看原文VeRL-Omni is a general RL training framework focused on multimodal generative models, built on top of verl. It originated from the multi-modal generation RL effort in verl, and now has a dedicated home so it can evolve in a more focused way. [2026-09] The v1 trainer (TransferQueue + ReplayBuffer) is now the default for diffusion models; the legacy v0 trainer is deprecated, while offline DPO remains on v0 by design. [2026-08] DiffusionOPD (on-policy distillation, including multi-teacher MOPD) is now supported. [2026-08] 🔥 MiniMax-H3 now supports T2VA, FL2VA, and Ref2VA with both FlowGRPO and D…
Topics / 标签
01
浏览全部相关推荐
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
其他人工智能更新于 2026-10-25
Developer-Y/cs-video-courses★ 83.8k
List of Computer Science courses with video lectures.
其他人工智能更新于 2026-10-24
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
其他人工智能更新于 2026-10-24
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
其他人工智能更新于 2026-10-25