Spark NLP 5.5 dramatically enhances the landscape of large language model (LLM) inference. This major release introduces native integration with Llama.cpp, unlocking access to tens of thousands of GGUF models available on Hugging Face – but now deployable at scale. Spark NLP 5.5 enables you to load any quantized model via the Llama.cpp library as a GGUF model. This capability extends across diverse computing environments – from local machines to single-node and multi-node setups – and seamlessly integrates with managed clusters on platforms like Databricks, AWS EMR, Azure, and Google Cloud Platform.A standout feature of this release is its hardware-agnostic approach, offering optimized performance across Intel processors, Nvidia CUDA GPUs, and Apple Silicon chips. This versatility ensures that organizations can leverage their existing infrastructure while scaling their LLM & NLP capabilities.As we celebrate reaching the milestone of 120 million downloads of Spark NLP, the 5.5 release puts tens of thousands of new models at your fingertips, ready to power the next generation of AI applications. Join us to explore how this release is set to redefine the boundaries of LLM inference – making it more scalable, efficient, and accessible than ever before.