Long-Context Modeling with Dynamic Hierarchical Sparse Attention for On-Device LLMs
Paper • 2510.24606 • Published
DHSA
-
-
sxiong/DHSA-Llama-3.1-8B-Instruct-BF16
Updated • 4 -
sxiong/DHSA-Llama-3.1-8B-Instruct-NF4
Updated • 559 -
sxiong/DHSA-Qwen2.5-3B-Instruct-BF16
Updated • 3 -
sxiong/DHSA-Gemma2-2b-it-BF16
Updated • 9 -
sxiong/DHSA_Long-Data-Collections
Viewer • Updated • 2.33M • 407 • 6 -
sxiong/DHSA_RULER
Preview • Updated • 126 • 1