Pinned Repositories
Smart-Infinity
[HPCA'24] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System
AI-strartup_team9
AI start up class of team 9
alpaca-lora
Instruct-tune LLaMA on consumer hardware
dacon_koreaNLI
DeepBinDiff_edited
docker-pyenv-poetry
A Docker image : pyenv-poetry
gpudirect_storage
hongsunjang.github.io
pipe-bd
[DATE 2023] Pipe-BD: Pipelined Parallel Blockwise Distillation
Vitis-Tutorials
Vitis In-Depth Tutorials
hongsunjang's Repositories
hongsunjang/pipe-bd
[DATE 2023] Pipe-BD: Pipelined Parallel Blockwise Distillation
hongsunjang/DeepBinDiff_edited
hongsunjang/docker-pyenv-poetry
A Docker image : pyenv-poetry
hongsunjang/gpudirect_storage
hongsunjang/Vitis-Tutorials
Vitis In-Depth Tutorials
hongsunjang/AI-strartup_team9
AI start up class of team 9
hongsunjang/alpaca-lora
Instruct-tune LLaMA on consumer hardware
hongsunjang/dacon_koreaNLI
hongsunjang/FlexGen
Running large language models on a single GPU for throughput-oriented scenarios.
hongsunjang/GCoD_
[HPCA 2022] GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design
hongsunjang/GenGNN_
hongsunjang/git_tutorial
hongsunjang/hands-on-ML
hongsunjang/hi-nest
Learning Nestjs by making enterprise PAI
hongsunjang/hongsunjang.github.io
hongsunjang/nuber-eats-backend
nuber-eats backend
hongsunjang/paper-review
hongsunjang/pipedream
hongsunjang/proxylessnas
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
hongsunjang/loss-landscape
Code for visualizing the loss landscape of neural nets
hongsunjang/NeutronStarLite
A Distributed GNN system
hongsunjang/notion_widgets
A set of HTML widgets that could be embedded into Notion.so https://www.notion.so/ pages. For more see https://blog.shorouk.dev/notion-widgets-gallery/
hongsunjang/remixer
hongsunjang/ring-attention-pytorch
Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch
hongsunjang/ringattention
Transformers with Arbitrarily Large Context
hongsunjang/Solved-Algorithm-Problems
hongsunjang/ssd-gpu-dma
Build userspace NVMe drivers and storage applications with CUDA support
hongsunjang/Vitis_Accel_Examples
Vitis_Accel_Examples
hongsunjang/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
hongsunjang/YBIGTA-pre-session