Activity
Stars and mentions · Last 30 days, Oct 6 – Nov 4
Top repositories
YeonwooSung’s repositories ranked by pull request authors, as on trending.
Contributes to
Repositories outside YeonwooSung’s account where YeonwooSung opened or reviewed pull requests in the past 365 days.
Who noticed YeonwooSung
Everyone who starred or forked YeonwooSung’s repositories since the archive began in 2011.
Notable accounts
Ordered by the stars their own repositories have received.
Biggest fans
Accounts that starred the most of these repositories.
Breakout weeks
Each repository’s best week of new stars, with the release published around it.
Achievements
Awards earned by the repositories YeonwooSung owns. Select an award to embed its badge.
No awards yet
Repositories earn awards by reaching the top three in a completed trending day or week.
A repository earns an award for finishing first, second or third in a completed trending day or week, ranked by new stars, new forks or pull request authors. Awards follow a repository through renames and transfers and count toward its current owner. Weeks run Monday to Sunday, UTC.
Mentions
别急着给 Claude Code 换模型，先看它到底在等什么、反复读什么、哪一步改坏了测试。 YeonwooSung/my-claude-code-mods 这组 Mods 补的是 Agent 的可观测性：profiler 拆解耗时并导出 OTLP，context-inspector 找上下文浪费，time-machine 用 shadow-git 快照回看每次工具调用、恢复或分支，loop-detective 抓失败重试循环。 值得关注的是把调试从猜测变成查证据。不过，多 Mods 同开时的开销和 UI 兼容性仍需实测。
Pour explorer le code et tester en local : 🔗 YeonwooSung/my-claude-code-mods
Supercharge your AI agent with these Claude Code... ⭐ GitHub Repository: YeonwooSung/my-claude-code-mods In this video, we explore my-claude-code-mods, an open-source project that custom TypeScript mods for Claude Code providing session profiling, context waste analysis, time-travel debugging with shadow-git, and loop detection.. #github #coding #opensource #programming #developer
读大模型架构，光看名词很容易把差异混在一起；这个仓库用 PyTorch 从头实现多种模型，把结构拆成可以对照的代码。 YeonwooSung/llm-architecture-from-scratch 从 GPT-2、Llama 到 DeepSeek、Gemma、Llama 4，注意力、位置编码、归一化和 MoE 都能逐个比较。记笔记时想提醒自己：架构不是一张配置表，读实现才能看清设计选择如何组合。
看开源 LLM 实现，最有价值的往往不是多一个模型，而是能把架构差异拆开对照。这个仓库用 PyTorch 从头实现多种模型，覆盖 GQA、滑动窗口注意力、MoE，也包括图文模型，适合追踪论文里的设计如何落到代码里。 YeonwooSung/llm-architecture-from-scratch 从 GPT-2、Llama 到 DeepSeek V3、Mistral 3.1 和 Llama 4 Maverick，逐个看归一化、位置编码和注意力机制，学到的不只是模型名称；大模型架构的取舍也更容易看清。