Skip to content
View jlee5814's full-sized avatar
4 followers · 6 following

Achievements

Achievement: Pull Sharkx3Achievement: YOLOAchievement: Pair Extraordinairex2Achievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: YOLOAchievement: Pair Extraordinairex2Achievement: Quickdraw

Block or report jlee5814

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
jlee5814/README.md

ML Systems and GPU Performance:

  • Active contributor to SGLang (MLX, UMA and MoE)
  • Low-precision quantizations across NVFP4, MI355X
  • Agent infra: persistent agent runtimes

Pinned Loading

  1. gameshark-runtime gameshark-runtime Public

    GameShark is a local-first runtime that gives individuals ownership of persistent AI agents, their memories, their permissions, and their ongoing responsibilities.

    Python

  2. sglang sglang Public

    Forked from sgl-project/sglang

    My SGLang contributions: high-performance LLM inference, Apple Silicon/MLX backends, MoE kernel optimization, and serving runtime improvements.

    Python

  3. cosmic-navi cosmic-navi Public

    Designed and deployed an autonomous agent simulation environment featuring persistent memory, real-world tool execution, and automated state tracking for multi-bot agents.

    Java

  4. agent-of-record agent-of-record Public

    Record-grounded AI agents for freight, healthcare, and finance, combining local LLMs with deterministic verification, permissions, and guardrails.

    Python