#Distributed Computing
Latest news articles tagged with "Distributed Computing". Follow the timeline of events, related topics, and entities.
Articles (4)
-
πΊπΈ GetBatch: Distributed Multi-Object Retrieval for ML Data Loading
[USA]
arXiv:2602.22434v1 Announce Type: cross Abstract: Machine learning training pipelines consume data in batches. A single training step may require thousands of samples drawn from shards distributed ac...
Related: #Machine Learning, #Data Optimization, #Storage Efficiency -
πΊπΈ veScale-FSDP: Flexible and High-Performance FSDP at Scale
[USA]
arXiv:2602.22437v1 Announce Type: cross Abstract: Fully Sharded Data Parallel (FSDP), also known as ZeRO, is widely used for training large-scale models, featuring its flexibility and minimal intrusi...
Related: #AI Training Optimization, #System Architecture -
πΊπΈ Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling
[USA]
arXiv:2503.04398v4 Announce Type: replace-cross Abstract: Prevailing LLM serving engines employ expert parallelism (EP) to implement multi-device inference of massive MoE models. However, the efficie...
Related: #Machine Learning Optimization, #LLM Efficiency -
πΊπΈ TimelyFreeze: Adaptive Parameter Freezing Mechanism for Pipeline Parallelism
[USA]
arXiv:2602.05754v1 Announce Type: cross Abstract: Pipeline parallelism enables training models that exceed single-device memory, but practical throughput remains limited by pipeline bubbles. Although...
Related: #Artificial Intelligence, #Machine Learning