Skip to content
View steven-kid's full-sized avatar
🎯
Focusing
🎯
Focusing
27 followers · 21 following
  • Beijing Normal University
  • China
  • 17:31 (UTC +08:00)

Achievements

Achievement: Pull SharkAchievement: Starstruckx2

Achievements

Achievement: Pull SharkAchievement: Starstruckx2

Block or report steven-kid

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
steven-kid/README.md

👋 Hey I'm Steven

I’m a engineer focused on AI agents and AI infrastructure. Passionate about building reliable, high-performance systems for the next generation of AI computing.

Coding

🚀 Technologies & Tools

Python PyTorch PyTorch vLLM qwen deepseek

🎯 2026 Goals

  • Advance AI agent infrastructure and improve long horizon agent performence
  • Contribute to high-performance LLM inference and serving systems
  • Build open-source tools that make AI development more reliable and accessible

Pinned Loading

  1. loopx-project/loopx loopx-project/loopx Public

    Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.

    Python 5.9k 561

  2. agent-earth/deepseek-harness-desktop agent-earth/deepseek-harness-desktop Public

    Minimal desktop wrapper for DeepSeek Harness 极简 Deespeek Harness 桌面端，跨平台，免配置，开箱即用

    JavaScript 230 16

  3. vllm-omni vllm-omni Public

    Forked from vllm-project/vllm-omni

    A framework for efficient model inference with omni-modality models

    Python