gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR和TTS的开源框架。

Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.

A dynamic analysis tool to detect floating-point errors in HPC applications.

A personal dynamic blog of mine which is messed with infinity build using Django. The blog has a minimalistic design using only two colors.

A Discord bot that counts to infinity

ColQwen2 local Vespa DB deploy and feed and Open-Webui retrieval function

docker compose to serve some local language models

Infinity Search Clone

the world Needs More Love ... so here is a bit of love sparkle

Finds what digit is placed on certain 0-based index in string of numbers from zero to infinity or from one to infinity

ColQwen2 via infinity embedding api and local vespa db sample