Found 2 document(s)
Page 1 of 1
-
LLMs on edge devices are constrained by limited memory and bandwidth. Although 1.58-bit ternary weights greatly reduce model storage, long-context inference is increasingly bottlenecked by KV-cache traffic and attention....
-
Hazardous material transportation is well-known for its high potential risk. An accident may cause very serious economic damage and negative impacts on the public health and the environment over the long term. Optimizati...