Skip to content
conftrace_

sequence parallelism

5 papers

Explore in graph

Also known as

SP

Co-occurring keywords · papers mentioning both

approximate attention (2) ring communication (1) model decoupling (1) ring self-attention (1) long sequence training (1) context block (1) transformer model (1) long sequence (1) long-context inference (1) visual language model (1)

Papers

APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention ACL 2026 PipeDiT: Accelerating Diffusion Transformers in Video Generation with Task Pipelining and Model Decoupling AAAI 2026 APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs ACL 2025 LongVILA: Scaling Long-Context Visual Language Models for Long Videos ICLR 2025 Sequence Parallelism: Long Sequence Training from System Perspective ACL 2023