-
HyperAccel
- Seoul, South Korea
- https://www.linkedin.com/in/daekyoung-jung-154807141/
- in/daekyoung-jung-154807141
Stars
NVFP4 inference framework for low-batch and long-decode reasoning
FlashInfer: Kernel Library for LLM Serving
This package contains the original 2012 AlexNet code.
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
An open source implementation of CLIP.
Achazwl / mlc
Forked from mlc-ai/mlc-llmMiniCPM on Android platform.
A high-throughput and memory-efficient inference and serving engine for LLMs
CMake toolchain file and other scripts for the Android NDK
A collection of pre-trained, state-of-the-art models in the ONNX format
QLoRA: Efficient Finetuning of Quantized LLMs
Wikitext format dataset of Namuwiki (Most famous Korean wikipedia)
Code of Programming Problems from Operating System Concepts
Solutions to Operating System Concepts Exercises, 9th Edition
Source code for the 10th edition of Operating System Concepts
Interactive visual analytic tool for exploring epigenomics data w/ associated metadata, powered by HiGlass and Gosling
Solutions to exercises and problems from "Introduction to Algorithms", Fourth Edition by Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest and Clifford Stein
Public domain software for processing and analyzing scientific images
Community Patch for Civilization V - Brave New World
Open-source Android/Desktop remake of Civ V
This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, s…
[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl