Local inferencing in one JVM JAR, dependency free, faster than llama.cpp
Every component of the AI stack, a la carte.
以下正文同步自 Hacker News 最新，版权归原站所有，已转换为易读排版。
Quixotic AI
Stack Examples Benchmarks
AI sovereignty for the JVM
Some call AI on the JVM quixotic.
We call it Quixotic AI.
Finally, AI in a jar.
Every component of the AI stack, a la carte.
AI inference engine. Chat, vision, embeddings and text-to-speech capabilities for the JVM, with Spring AI and LangChain4j integrations.
Fast quantized matrix-multiplication routines.
TikToken-compatible and customizable tokenizers for popular LLM models.
Multi-backend tensor engine, in the works. Java, C, CUDA, HIP, Metal, OpenCL, and Mojo. Write once, accelerate everywhere.
Pure Java, read and write support for llama.cpp's GGUF model format.
Pure Java, read and write support for HuggingFace's Safetensors format.
正文由 探How 从来源站点 RSS 同步，内容未经改写；遇到排版缺失或需要图片、视频时请以原文为准。