Skip to content
View 00fish0's full-sized avatar
🎯
Learning DB
🎯
Learning DB
33 followers · 75 following
  • Harbin Institute of Technology, ShenZhen
  • Shenzhen, China
  • 10:03 (UTC +08:00)

Achievements

Achievement: Pair Extraordinairex2Achievement: QuickdrawAchievement: Pull Sharkx2

Achievements

Achievement: Pair Extraordinairex2Achievement: QuickdrawAchievement: Pull Sharkx2

Highlights

  • Pro

Block or report 00fish0

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
00fish0/README.md

Hi there 👋 My name is Zihan Tang.

I am currently an undergraduate (2023-2027) student in Computer Science and Technology at Harbin Institute of Technology, Shenzhen (HITSZ). My research focus is on machine learning systems, with an emphasis on LLM serving infrastructure.

🔭 I'm currently working on the systems substrate for large language model serving. Specifically, my focus includes KV cache transport and storage across GPU memory, RDMA, and distributed store backends, high availability for distributed KV cache services, and TCP/RDMA transport internals. I also contribute upstream and downstream across the vLLM/SGLang ecosystem and work on AI infrastructure deployment and tuning. Additionally, I'm exploring on-device inference acceleration.

📫 How to reach me:

Email GitHub WeChat

🤔 I'm also passionate about open-source community building and LLM serving systems. Welcome experts from both academia and industry to connect with me.

✨ Feel free to reach out via email for any related questions.

Stack

C++ / CUDA / Python / Rust / RDMA / PyTorch / vLLM / SGLang / Mooncake

Pinned Loading

  1. kvcache-ai/Mooncake kvcache-ai/Mooncake Public

    Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

    C++ 5.6k 849

  2. sgl-project/sglang sgl-project/sglang Public

    SGLang is a high-performance serving framework for large language models and multimodal models.

    Python 29k 6.5k

  3. alibaba/yalantinglibs alibaba/yalantinglibs Public

    A collection of modern C++ libraries, include coro_http, coro_rpc, compile-time reflection, struct_pack, struct_json, struct_xml, struct_pb, easylog, async_simple etc.

    C++ 2.1k 325