Skip to content
View AllenJWZhu's full-sized avatar
25 followers · 44 following
  • Meta
  • Sunnyvale, CA
  • 18:57 (UTC -05:00)

Achievements

Achievement: YOLOAchievement: Pull SharkAchievement: Public SponsorAchievement: QuickdrawAchievement: Starstruck

Achievements

Achievement: YOLOAchievement: Pull SharkAchievement: Public SponsorAchievement: QuickdrawAchievement: Starstruck

Highlights

  • Pro

Block or report AllenJWZhu

Report abuse

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

Report abuse
AllenJWZhu/README.md

致瞬息万变之物 · 及亘古不变之物

ML System Protection Association, save your GPU, save lives.

About Me

I’m Allen Zhu – I build high-performance machine-learning systems

  • 🔬 Now — SWE Intern @ Meta (Facebook) • AI Infra
  • ⚙️ Before — Research Intern @ SenseTime • AI Lab & SWE Intern @ iFLYTEK • Speech AI
  • ✍️ Writing — large language model, machine learning systems, high performance computing (Medium / 知乎)
  • 🧐 Seeking — full-time ML Systems / Infra roles=
  • 🎯 Side quests — photography, strategy games, pokemon enjoyer

🗂️ Timeline

gantt dateFormat YYYY-MM title Work Experience section Experience Meta – ML Infra Intern (C++/CUDA) :a1, 2025-05, 3m SenseTime – Research Intern (LLM Quantization) :a2, 2024-12, 2m iFLYTEK – Software Engineer Intern (Speech AI) :a3, 2024-08, 3m
Loading

🧰 Tech Stack

Languages ML Systems / HPC Cloud & DevOps

☕ Reach Out

Pinned Loading

  1. LlamaInfer LlamaInfer Public

    LLM Inference Engine: High-performance CUDA-accelerated framework for large language model inference A cutting-edge, open-source implementation of a large language model (LLM) inference engine, opt…

    C++ 11 3

  2. sglang sglang Public

    Forked from sgl-project/sglang

    SGLang is a fast serving framework for large language models and vision language models.

    Python

  3. verl verl Public

    Forked from volcengine/verl

    verl: Volcano Engine Reinforcement Learning for LLMs

    Python

  4. BERT_TensorRT_Inference_Optimization BERT_TensorRT_Inference_Optimization Public

    Inference optimization of the BERT model using TensorRT, NVIDIA's high-performance deep learning inference platform. TensorRT is designed to maximize the efficiency of deep learning models during i…

    5

  5. Distributed-PoW-based-Fault-Tolerant-Blockchain-System Distributed-PoW-based-Fault-Tolerant-Blockchain-System Public

    Proof-of-Work Blockchain Consensus System: A high-performance, modular implementation of a decentralized blockchain network This project is a robust and scalable implementation of a Proof-of-Work (…

    Go 1

  6. CMU_Course_Notes CMU_Course_Notes Public

    This is the combined collection of the course notes for some of the computer science classes at CMU released online.

    65 15