#
Starred repositories
ποΈ Reactive Programming paradigm for Go: declarative and composable API for event-driven applications
LongCat Audio Tokenizer and Detokenizer
Tiny AutoEncoder for Hunyuan Video (and other video models)
Stars1233 / flash-attention
Forked from Dao-AILab/flash-attentionFast and memory-efficient exact attention
Fast and memory-efficient exact attention
A sparse attention kernel supporting mix sparse patterns
Enjoy the magic of Diffusion models!
Enjoy the magic of Diffusion models!
Towards Real-Time Diffusion-Based Streaming Video Super-Resolution β An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional deβ¦
Demystifying Reinforcement Learning in Agentic Reasoning
UI5 Web Components - the enterprise-flavored sugar on top of native APIs! Build SAP Fiori user interfaces with the technology of your choice.
π₯ AI-powered data enrichment tool that transforms emails into rich datasets with company profiles, funding data, tech stacks, and more using Firecrawl and multi-agent AI
π₯ Visual workflow builder for AI agents powered by Firecrawl - drag-and-drop web scraping pipelines with real-time execution
π₯ Visual workflow builder for AI agents powered by Firecrawl - drag-and-drop web scraping pipelines with real-time execution
NEO Series: Native Vision-Language Models from First Principles
Stars1233 / RAG-Anything
Forked from HKUDS/RAG-Anything"RAG-Anything: All-in-One RAG Framework"
"RAG-Anything: All-in-One RAG Framework"
An application observability facade for the most popular observability tools. Think SLF4J, but for observability.
OpenXRLab foundational library for XR-related algorithms
OpenXRLab Visual-inertial SLAM Toolbox and Benchmark
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
This repository contains example applications to illustrate the different capabilities of GraalVM
GraalVM compiles applications into native executables that start instantly, scale fast, and use fewer compute resources π