Code for explaining and evaluating late chunking (chunked pooling)

Official Implementation of "Multi-Head RAG: Solving Multi-Aspect Problems with LLMs"

Production-ready platform for agentic workflow development.

A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Apache Spark - A unified analytics engine for large-scale data processing

A high-throughput and memory-efficient inference and serving engine for LLMs

A framework for few-shot evaluation of language models.

Awesome-LLM: a curated list of Large Language Model

🤗 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.