/AI2h ago

NVIDIA Releases FlashDreams Open-Source Library For Faster World Model Inference

--0--
Original posts
Ruilong Li
Quote posts
Sanja Fidler#512
Reposts
Sanja Fidler#512
Original postSanja Fidler#512
Ruilong Li@ruilong_li

World models are moving beyond offline generation towards interactive, real-time experiences.

Introducing ⚡FlashDreams⚡: an open-source high-performance inference and serving library built for autoregressive world models:

🔥 Up to 3.10× faster LingBot-World inference 🔥 Up to 2.12× faster Self-Forcing inference 🔥 Up to 1.40× faster Wan2.1 inference 🔥 8 integrated models 🔥 Multi-GPU, streaming, low-latency serving 🔥 Agentic skills that teach you how to use it

FlashDreams is designed for a new generation of AI systems that continuously evolve over time while responding to user interactions. It powers applications across robotics, autonomous vehicle simulation, gaming, and virtual worlds.

Github: https://github.com/NVIDIA/flashdreams Docs: https://nvidia.github.io/flashdreams Research page: https://research.nvidia.com/labs/sil/projects/flashdreams/ Join the #flashdreams Discord channel at https://discord.gg/yTdHDqFP

FlashDreams is also the runtime backbone behind NVIDIA OmniDreams (https://github.com/nv-tlabs/omni-dreams)

1/n

#AI #WorldModels #FastInference #PhysicalAI #OpenSource #NVIDIA

8:04 AM · Jun 3, 2026 · 6.5K Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS970BOOKMARKS1LIKES12RETWEETS3
Sanja Fidler@FidlerSanja

Super excited to open source Flashdreams, acceleration library for world models! No restrictions on usage, Apache 2 license.

World models are the next frontier for video generation and paramount to Physical AI.

Flashdreams yields out of the box speed up across world models

Ruilong Li@ruilong_li

World models are moving beyond offline generation towards interactive, real-time experiences.

Introducing ⚡FlashDreams⚡: an open-source high-performance inference and serving library built for autoregressive world models:

🔥 Up to 3.10× faster LingBot-World inference 🔥 Up to 2.12× faster Self-Forcing inference 🔥 Up to 1.40× faster Wan2.1 inference 🔥 8 integrated models 🔥 Multi-GPU, streaming, low-latency serving 🔥 Agentic skills that teach you how to use it

FlashDreams is designed for a new generation of AI systems that continuously evolve over time while responding to user interactions. It powers applications across robotics, autonomous vehicle simulation, gaming, and virtual worlds.

Github: https://github.com/NVIDIA/flashdreams Docs: https://nvidia.github.io/flashdreams Research page: https://research.nvidia.com/labs/sil/projects/flashdreams/ Join the #flashdreams Discord channel at https://discord.gg/yTdHDqFP

FlashDreams is also the runtime backbone behind NVIDIA OmniDreams (https://github.com/nv-tlabs/omni-dreams)

1/n

#AI #WorldModels #FastInference #PhysicalAI #OpenSource #NVIDIA

1hViews 970Likes 12Bookmarks 1