Gyeong-In Yu
6 papers · 2019–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (4) π Interdisciplinary Bridge π Cross-Pollinator (12)
πΊοΈ
Taxonomy Completionist
(13)
π₯
Unstoppable
(5)
Conferences
NIPS (2)
OSDI (2)
ICML (1)
NSDI (1)
Top co-authors
Keywords
deep learning framework
(3)
imperative programming
(2)
training optimization
(1)
deep learning training
(1)
model serving
(1)
distributed training
(1)
model compilation
(1)
generative model
(1)
pipeline parallelism
(1)
inference optimization
(1)
feature engineering
(1)
neural network compilation
(1)
symbolic execution
(1)
compiler optimization
(1)
inference serving
(1)
batch scheduling
(1)
parallel execution
(1)
tensor computation
(1)
dataflow graph
(1)
distributed serving
(1)
Papers
BPipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models
ICML 2023
Orca: A Distributed Serving System for Transformer-Based Generative Models
OSDI 2022
Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs
NIPS 2021
Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning
NIPS 2020
A Tensor Compiler for Unified Machine Learning Prediction Serving
OSDI 2020
JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs
NSDI 2019