LLM inference in C/C++

A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.

A collection of pre-trained, state-of-the-art models in the ONNX format

Making large AI models cheaper, faster and more accessible

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Netease Youdao's open-source embedding and reranker models for RAG products.

AMD Ryzen™ AI Software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen™ AI powered PCs.

Third-party test scripts and bug tracking for SCALE

Use BERT pre-trained model to do sentiment classification

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Lustre HSM tools

Ostro OS BSP