About Me

Table of Contents

Overview
#

Shanshan Shen | 申杉杉

September 18th, 1998

I am currently a software engineer working at Huawei Ascend, focusing on LLM/VLM inference and GPU/NPU computing. I have contributed to some popular open source projects such as vLLM, to build a easy-to-use software ecosystem for Ascend. Before this, I was a student at Beijing Jiao Tong University (BSc/MSc), majoring in communication engineering. You can see my projects at Github, or see my posts at Zhihu.

Experiences
#

Huawei
Software Engineer
July '23 - Present
Working at Huawei Ascend, building vLLM inference engine, previously at Quality and Process IT Department.
Beijing Jiao Tong University
Postgraduate Student
September '21 - June '23
Studying at School of Electronic and Information Engineering, focusing on wireless communication NAS layer security.
Beijing Jiao Tong University
Undergraduate Student
September '16 - June '20
Studying at School of Electronic and Information Engineering, majoring in communication engineering.

Open Source Contributions
#

During my open source experience, I have become:

Outside collaborator of vllm.
Core contributor to vllm-ascend.
Contributor to vllm-omni.

vllm-project/vllm

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

Python

71649

13846

vllm-project/vllm-ascend

Community maintained hardware plugin for vLLM on Ascend

Python

1717

866

vllm-project/vllm-omni

A framework for efficient model inference with omni-modality models

Python

2870

471

In addition, I have contributed 131 PRs to the vLLM ecosystem, focusing on multi-modal inference, structured output and elastic scaling. Find more details about all PRs I have contributed here.