2 रिपॉजिटरी
Buffers used to decouple high-frequency generative input and output operations to prevent data bottlenecks.
Distinct from Queue-Based Buffers: Focuses on decoupling AI generation I/O rather than simple byte-sequence shifting in memory.
Explore 2 awesome GitHub repositories matching data & databases · Asynchronous Generation Buffers. Refine with filters or upvote what's useful.
StreamDiffusion is an interactive generative AI framework and inference engine designed for the low-latency delivery of image and video streams. It provides a real-time Stable Diffusion pipeline for text-to-image and image-to-image generation, enabling the creation of continuous generative image streams with minimized computational delay. The framework optimizes throughput using a pre-computed cache engine and residual-based guidance approximation to reduce the number of required model passes. It further manages GPU load through similarity-based frame skipping, which avoids redundant computat
Employs dedicated asynchronous queues to decouple input and output operations during high-frequency image generation.
Glass is an AI desktop assistant and screen-to-LLM interface that processes visual and auditory context from a computer to automate tasks. It functions as a tool for screen analysis, bridging real-time desktop captures with large language models to extract semantic meaning and data insights. The system enables AI-assisted desktop interaction by recording live screen and audio data to provide a persistent digital memory for processing. This allows the application to analyze visible screen information and trigger automation workflows through global keyboard shortcuts.
Implements buffers to decouple high-frequency screen and audio captures from high-latency LLM inference.