-
Sequence Parallelism: Long Sequence Training from System Perspective
Paper • 2105.13120 • Published • 5 -
Ring Attention with Blockwise Transformers for Near-Infinite Context
Paper • 2310.01889 • Published • 13 -
Striped Attention: Faster Ring Attention for Causal Transformers
Paper • 2311.09431 • Published • 4 -
DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
Paper • 2309.14509 • Published • 20
Maozhou Ge
Gmc2
AI & ML interests
None yet
Recent Activity
new activity
3 days ago
internlm/POLAR-7B:Any plan to open source the dataset?
upvoted
a
paper
10 days ago
Pre-Trained Policy Discriminators are General Reward Models
liked
a Space
13 days ago
Victarry/PP-schedule-visualizer
Organizations
None yet