conftrace_

memory optimization

114 papers

Explore in graph

Co-occurring keywords

model compression (3302) large language model (13587) memory efficiency (261) kv cache (74) inference optimization (219) inference efficiency (248) efficient inference (233) edge computing (210) deep neural network (1803) efficient computing (781)

Papers

A fast heuristic to optimize time-space tradeoff for large models NIPS 2023
Coop: Memory is not a Commodity NIPS 2023
OSDP: Optimal Sharded Data Parallel for Distributed Deep Learning IJCAI 2023
H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training NIPS 2023
A Survey on Efficient Training of Transformers IJCAI 2023
Efficient Beam Tree Recursion NIPS 2023
An In-depth Study of Stochastic Backpropagation NIPS 2022
Memory-Efficient Training of RNN-Transducer with Sampled Softmax INTERSPEECH 2022
BMInf: An Efficient Toolkit for Big Model Inference and Tuning ACL 2022
Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction NIPS 2022
Deep Equilibrium Optical Flow Estimation CVPR 2022
GACT: Activation Compressed Training for Generic Network Architectures ICML 2022
POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging ICML 2022
Graph Reordering for Cache-Efficient Near Neighbor Search NIPS 2022
Be Like Water: Adaptive Floating Point for Machine Learning ICML 2022
A*+BFHS: A Hybrid Heuristic Search Algorithm AAAI 2022
Piper: Multidimensional Planner for DNN Parallelization NIPS 2021
Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup IJCNLP 2021
Efficient Combination of Rematerialization and Offloading for Training DNNs NIPS 2021
Multi-split Reversible Transformers Can Enhance Neural Machine Translation EACL 2021
Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup ACL 2021
AC-GC: Lossy Activation Compression with Guaranteed Convergence NIPS 2021
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU ICCV 2021
How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task ACL 2021
Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs CVPR 2021