kunkun

AI Infra / HPC Working on vLLM / vLLM-Omni Interested in inference systems, GPU kernels, multimodal serving

代表作品 / 项目

kunkunblueberry⭐ 0AI Systems · LLM Inference · HPC
vllm-rlt⭐ 0vllm based inference engine for looped transformer
vllm-omni⭐ 0A framework for efficient model inference with omni-modality models
vllm⭐ 0A high-throughput and memory-efficient inference and serving engine for LLMs
skills-review-pull-requests⭐ 0My clone repository

条目信息来自其公开主页与公开发布内容。按本站规范，页面不展示任何联系方式。需要更正或删除？通过收录与更正通道提交，24 小时内处理。