Productive, portable, and performant GPU programming in Python
20+ high-performance LLMs with recipes to pretrain, finetune at scale
Kubernetes observability and automation
A general fine-tuning kit geared toward image/video/audio diffusion
Maimaibot, a (more focused) multi-platform intelligent agent
Qwen3-omni is a natively end-to-end, omni-modal LLM
Ark pixel font - Open source Pan-CJK pixel font
Open-source deep-learning framework for building and training
RAG Search API
ZAPI by Adopt AI is an open-source Python library
Helps developers deploy LangChain runnables and chains as a REST API
A Next-Generation Training Engine Built for Ultra-Large MoE Models
SDK for building interactive UI components over MCP for AI tools
Skills for threat modeling, scanning, triage, patching, etc.
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
Multi-modal large language model designed for audio understanding
Open-source framework for intelligent speech interaction
Benchmarking synthetic data generation methods
AIMET is a library that provides advanced quantization and compression
Recognition and resolution of numbers, units, date/time, etc.
Communicate with an LLM provider using a single interface
Fast and memory-efficient exact attention
Deepnote is a drop-in replacement for Jupyter
NeurIPS2025 Spotlight] Quantized Attention
Document Index for Vectorless, Reasoning-based RAG