Skip to content
View Momoyeyu's full-sized avatar
27 followers · 15 following

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Quickdraw

Block or report Momoyeyu

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.

Content in all repositories owned by your account will be closed.
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
momoyeyu/README.md

Momoyeyu · 墨末夜羽 · AI Systems Engineer. Making intelligence work efficiently.

关注 AI 的成本与性能，从模型能力到系统落地。

曾在 宇宙厂 与 某明星初创 实习，做过基础设施与 Agent 产品。

Agent Harness: tools, context, evaluation. AI Infra: serving, efficiency, scale. Post-training: SFT, RL, alignment.

Python C++ Go PyTorch Linux Docker Git

On GitHub: this year's public contributions, current streak and longest streak. Updated daily; date shown in the image.

A pale purple snake follows this year's contribution trail, drawn in grey-blue squares.

平时打乒乓球，也弹吉他。
曾组织乒乓球社团，喜欢把一群人聚到一起做事。

Blog · 小红书 · Bilibili

Code, then play.

Pinned Loading

  1. tt-a1i/archify tt-a1i/archify Public

    Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

    JavaScript 88.4k 6k

  2. 666ghj/MiroFish 666ghj/MiroFish Public

    A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

    Python 81.6k 12.4k

  3. Tencent-Hunyuan/UniRL Tencent-Hunyuan/UniRL Public

    UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

    Python 1k 104

  4. MakazhanAlpamys/Soup MakazhanAlpamys/Soup Public

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

    Python 9.6k 1.6k

  5. autodev autodev Public

    Open the black box of vibe coding. A clarify-first Agent Skill | 打开 VibeCoding 的黑盒：一款对齐优先的 Skill

    HTML 8

  6. landable landable Public

    An agent skill that finds open-source issues where your PR can actually land — interest-driven scouting, acceptance evidence, tested patches, with human gates on what to pursue and what to publish

    JavaScript 9