Skip to content
View xianweihuihuan's full-sized avatar

Block or report xianweihuihuan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
xianweihuihuan/README.md



✨「 取法乎上,仅得其中;取法乎中,斯为下矣。」



C C++ Go Python Assembly


🧑‍💻 About Me

  • 🎓 西安邮电大学 在读,专注 系统底层基础架构 方向
  • 🐧 熟悉 Linux 系统编程网络编程,扎实的系统底层功底
  • 🔬 深入研究 操作系统内核数据库引擎分布式系统 三大核心领域
  • 🤖 持续探索 LLM 推理优化(vLLM / PagedAttention)与 AI Agent 前沿技术
  • 🏅 注重 底层原理,不满足于会用,追求知其然更知其所以然

⚙️ Tech Stack



🖥️ 操作系统内核 🗄️ 数据库引擎 🌐 分布式系统 🤖 AI / LLM
Bootloader Buffer Pool Raft 共识 vLLM
中断 / 内存管理 B+ Tree 索引 MapReduce PagedAttention
进程调度 Query Execution Distributed KV Continuous Batching
x86 Assembly 并发控制 Fault Tolerance AI Agent

🏆 What I've Built & Studied

  项目 简介 语言
🖥️ xianwei_OS 自研操作系统 — 从 Bootloader 到用户态全链路实现 C x86 ASM
🗄️ CMU 15-445 CMU 顶级数据库课程 — Buffer Pool / B+Tree / 并发控制 C++
🌐 MIT 6.8540 MIT 分布式系统 — Raft / MapReduce / Distributed KV Go
🤖 vLLM 系列 LLM 高性能推理引擎架构与源码研究 Python

📊 GitHub Analytics





Pinned Loading

  1. 6.8540 6.8540 Public

    Go

  2. CMU15445 CMU15445 Public

    C++

  3. nano-vllm-learn nano-vllm-learn Public

    Forked from GeeeekExplorer/nano-vllm

    Nano vLLM

    Python

  4. vllm-learn vllm-learn Public

    Forked from vllm-project/vllm

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Python