#
martinou
Follow
Starred repositories
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Fast and accurate automatic speech recognition (ASR) for edge devices
DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.
Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥
A powerful coding assistant application that integrates with the DeepSeek API to process user conversations and generate structured JSON responses. Through an intuitive command-line interface, it c…
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Janus-Series: Unified Multimodal Understanding and Generation Models
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Profile-Based Long-Term Memory for AI Applications
SGLang is a fast serving framework for large language models and vision language models.
Using APPL to reimplement popular algorithms for Large Language Models (LLMs) and prompts
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks
修正文档扭曲/模糊/阴影等情况，使用onnx模型简单轻量部署，未来持续跟进最新最好的文档矫正方案和模型,Correct document distortion using a lightweight ONNX model for easy deployment. We will continue to follow and integrate the latest and best docu…
Rill Flow is a high-performance, scalable workflow orchestration engine for distributed workloads and LLMs
DSPy: The framework for programming—not prompting—language models
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
A set of beautifully-designed, accessible, and customizable components to help you build your component library. Open Source.
Scalable RL solution for advanced reasoning of language models
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Enjoy the magic of Diffusion models!
An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
🤖 The semantic engine for LLMs, bringing semantic context to AI agents. 🔥