Skip to content
View Richardyu114's full-sized avatar
:shipit:
Focusing
:shipit:
Focusing
49 followers · 51 following

Achievements

Achievement: QuickdrawAchievement: Pull SharkAchievement: YOLOAchievement: Starstruckx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: QuickdrawAchievement: Pull SharkAchievement: YOLOAchievement: Starstruckx2Achievement: Arctic Code Vault Contributor

Organizations

@simvisionX

Block or report Richardyu114

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
Richardyu114/README.md

Hi, I'm Richard 👋 — an engineer working on LLM inference systems.

I spend most of my time around vLLM, CUDA, performance bottlenecks, and the practical side of making large models run well.

Now

  • Working on inference systems
  • Studying GPU performance and CUDA
  • Building small tools for research and engineering workflows

Notes

I like systems that are fast, simple, and honest about their trade-offs.

Trying to work hard and stop talking too much.

Pinned Loading

  1. vllm vllm Public

    Forked from vllm-project/vllm

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

    Python

  2. Moryn Moryn Public

    Moryn is a personal memory, skill, and soul layer for AI agents.

    TypeScript 4

  3. RPG-Infer RPG-Infer Public

    (experimental demo with codex) A distributed LLM inference runtime evolving toward a stateful cognitive runtime with session-, trajectory-, graph-, and memory-aware execution.

    Rust