Skip to content
View R3pere's full-sized avatar
🏠
Working from home
🏠
Working from home
  • University of Science and Technology of China
  • Anhui Hefei

Block or report R3pere

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. 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
R3pere/README.md

header

Always learning, always building.



Profile views Followers Focus


πŸ‘¨β€πŸ’» About Me

  • πŸŽ“ Software Engineering student at USTC
  • βš™οΈ Currently exploring AI Infrastructure
  • πŸš€ Interested in GPU computing, LLM serving, and inference optimization
  • 🌱 Learning and building with CUDA, C++, Python, vLLM, SGLang, PyTorch, and TensorRT

πŸ”— Connect With Me

GitHub ethan.z@mail.ustc.edu.cn


πŸ› οΈ Tech Stack

Languages

C++ Python

AI Infrastructure & Acceleration

CUDA vLLM SGLang PyTorch TensorRT

Tools & Platforms

Git VS Code PyCharm Linux


🐍 Contribution Snake

GitHub contribution snake

footer

Popular repositories Loading

  1. R3pere R3pere Public

  2. ai-infra-notes ai-infra-notes Public

    transformer,Pytorch,deep learning etc.

  3. edge-claw edge-claw Public

    Python

  4. nano-vllm-spec-decode nano-vllm-spec-decode Public

    Speculative decoding (n-gram / draft model, dynamic k) and vLLM V1-style mixed batching on nano-vllm, benchmarked against vLLM on A100

    Python

  5. nano-vllm-triton-kernels nano-vllm-triton-kernels Public

    Triton kernels and a fused QK-norm + RoPE + paged-KV-write kernel for nano-vllm

    Python