Lists (3)
Stars
Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!
An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models
Supercharge Your LLM with the Fastest KV Cache Layer
zgsm-ai / costrict
Forked from RooCodeInc/Roo-CodeCostrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.
A Datacenter Scale Distributed Inference Serving Framework
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
✔（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】
🔥🔥性能优化，服务监控方面的知识往往涉及量广且比较零散，希望将这部分知识整理成册，愿以后性能排查不再抓瞎。
Modular and structured prompt caching for low-latency LLM inference
Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
Transformer related optimization, including BERT, GPT
Out-of-box mtcnn detector using onnxruntime or opencv
Synthesizing and manipulating 2048x1024 images with conditional GANs
KSAI Lite is a deep learning inference framework of kingsoft, based on tensorflow lite
基于 Gin 进行模块化设计的 API 框架，封装了常用功能，使用简单，致力于进行快速的业务研发。比如，支持 cors 跨域、jwt 签名验证、zap 日志收集、panic 异常捕获、trace 链路追踪、prometheus 监控指标、swagger 文档生成、viper 配置文件解析、gorm 数据库组件、gormgen 代码生成工具、graphql 查询语言、errno 统一定义错误码…
🚀Vite+Vue3+Gin拥有AI辅助的基础开发平台，企业级业务AI+开发解决方案，支持TS和JS混用。它集成了JWT鉴权、权限管理、动态路由、显隐可控组件、分页封装、多点登录拦截、资源权限、上传下载、代码生成器、表单生成器和可配置的导入导出等开发必备功能。