Skip to content
View YiBangWon's full-sized avatar

Block or report YiBangWon

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. 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
YiBangWon/README.md

header

Python C++ CUDA PyTorch TVM Triton

Hi, I'm Hansol (Henry) Son

M.S. student at Yonsei University ASO Lab, working on AI systems — deep learning compilers, GPU kernel optimization, and LLM inference serving.

Research interests

  • Deep learning compilers — tensor program auto-tuning, TVM, Triton, torch.compile
  • LLM inference serving — vLLM / SGLang internals, speculative decoding, KV-cache management
  • LLM-guided systems optimization — using LLMs to steer compiler and kernel search

Selected work

Project What it does
adaptive-transfer-reasoning-compiler Transfer memory for low-budget matmul auto-tuning — 1.188× compiled-runtime speedup
profbridge-llm-guided-gpu-kernel-optimization Profiler-aware evaluation of LLM-generated GPU kernel candidates
shared-mcts-compiler-optimization Multi-model shared MCTS for TVM tensor program optimization
rgta-mtmapd Regret-guided online task-group assignment for multi-agent pickup & delivery

Elsewhere

Pinned Loading

  1. adaptive-transfer-reasoning-compiler adaptive-transfer-reasoning-compiler Public

    Adaptive transfer memory for low-budget CPU matmul tuning, with 1.188x compiled runtime speedup over Reasoning Compiler

    Python

  2. profbridge-llm-guided-gpu-kernel-optimization profbridge-llm-guided-gpu-kernel-optimization Public

    Research prototype for profiler-aware evaluation of LLM-generated GPU kernel optimization candidates.

    Python

  3. shared-mcts-compiler-optimization shared-mcts-compiler-optimization Public

    Multi-model shared MCTS for Reasoning Compiler-style TVM tensor program optimization.

    Python

  4. rgta-mtmapd rgta-mtmapd Public

    Online task-group assignment with regret-guided selection for multi-task multi-agent pickup and delivery (MT-MAPD). Code and results for the paper.

    Python

  5. multi-robot-fleet-management-system multi-robot-fleet-management-system Public

    ROS 2 multi-robot fleet management system for logistics automation.

    C++

  6. App-for-Red-Velvet-fans-using-flutter App-for-Red-Velvet-fans-using-flutter Public

    Cross-platform Flutter photo-card app for Red Velvet fans.

    Dart 1