Shypd.aiThe largest open index of AI toolsJlama is an open-source LLM inference engine for Java that allows developers to integrate large language models directly into their applications. It supports various models including Llama, Mistral, and Gemma, and offers features like paged attention and distributed inference.
Trending
About
Jlama is a modern, open-source LLM inference engine specifically designed for Java applications. It enables developers to seamlessly integrate and run large language models directly within their Java projects, eliminating the need for external services. The engine supports a wide range of popular models, including Gemma, Llama, Mistral, Qwen2, IBM Granite, GPT-2, and BERT. Key features include paged attention, mixture of experts, tool calling, and support for various data types and quantization levels. Jlama also offers distributed inference capabilities and a command-line interface for easy local use, making it a versatile solution for Java-based AI development.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
