重點導讀
vLLM-Omni 加入 Runway 的 Praxis-1 Day-0 支援,可根據攝影機觀測、機器人狀態與任務指令產生動作片段。
- 模型特性:Praxis-1 以大規模影片預訓練用於機器人控制,採 Apache 2.0 開放權重,並可適配不同機器人形態。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
推薦理由
整合說明涵蓋輸入資料、動作輸出與服務方式,呈現 Praxis-1 接入 vLLM-Omni 的實作範圍。
vLLM@vllm_project
·11 天前
🎉 Day-0 support for @runwayml’s Praxis-1 in vLLM-Omni!
From watching the world to acting in it: Praxis-1 brings large-scale video pretraining to robot control, with open weights under Apache 2.0 and adaptation across robot embodiments.
vLLM-Omni takes camera observations, robot state and a task instruction to generate action chunks. The integration supports offline inference and OpenPI / Positronic serving, with session history and reset handling. Qualified on a single @NVIDIA H100 80GB.
Thanks to the Runway and @Inferact teams for bringing this together.
推文來源 · X (Twitter)在 X 參與討論