Skip to content
View lambda7xx's full-sized avatar
258 followers · 1.2k following
  • Shanghai Jiao Tong University

Achievements

Achievement: YOLOAchievement: Starstruckx2Achievement: Pull Sharkx2Achievement: Quickdraw

Achievements

Achievement: YOLOAchievement: Starstruckx2Achievement: Pull Sharkx2Achievement: Quickdraw

Highlights

  • Pro

Organizations

@cs61

Block or report lambda7xx

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
lambda7xx/README.md

👋 Hi, I’m Xiao and I recently graduated from SJTU. I'm currently seeking a USA PhD position starting Fall 2025.

Research Interests:

  • Cloud Computing
  • Machine Learning Systems
  • Currently working on LLM Serving Systems.

Publications:

  • ICSE-SEIP'23
  • Eurosys'24
  • ASPLOS'24
  • RagInfer (OSDI'25 submission)
  • AgentServing (OSDI'25 submission, co-first author)

Projects

  • Aceso: Auto Parallel DNN Training
  • Raginfer: low latency RAG inference system
  • Autellix: high throuhput LLM agent serving system
  • DeepScaler: RL LLM training

Google Scholar

Google Scholar

📫 Feel free to email me at [email protected] for any inquiries or discussions.

Pinned Loading

  1. chinese-poetry chinese-poetry Public

    Forked from LC-John/chinese-poetry

    最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

    Python

  2. awesome-AI-system awesome-AI-system Public

    paper and its code for AI System

    272 20

  3. vllm-project/vllm vllm-project/vllm Public

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

    Python 38.8k 5.8k

  4. FastChat FastChat Public

    Forked from lm-sys/FastChat

    An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

    Python

  5. deepscaler deepscaler Public

    Forked from agentica-project/deepscaler

    Democratizing Reinforcement Learning for LLMs

    Python