Starred repositories
A high-throughput and memory-efficient inference and serving engine for LLMs
LangChain4j is an open-source Java library that simplifies the integration of LLMs into Java applications through a unified API, providing access to popular LLMs and vector databases. It makes impl…
Spec-driven development (SDD) for AI coding assistants.
Open-source search and retrieval database for AI applications.
Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Su…
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Integrate the DeepSeek API into popular softwares
Kimi K2 is the large language model series developed by Moonshot AI team
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i…
Stable Diffusion web UI
FlashMLA: Efficient Multi-head Latent Attention Kernels
Vulkan compute tool for testing video memory stability
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
Janus-Series: Unified Multimodal Understanding and Generation Models
Fully open reproduction of DeepSeek-R1
Distribute and run LLMs with a single file.
Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis; ICLR 2024 Spotlight; Official code
GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code