LLM Digest

Story

arxiv_cs_ai · Nov 10, 2026 · paper

Source brief

Joint Quantization and Dynamic Partitioning for Context-Aware Edge Vision Transformers

arxiv.orgNov 10, 2026
original source linked

In brief

Deploying vision transformer models across connected and automated vehicles (CAVs) requires joint management of computation and Vehicle-to-Vehicle (V2V) communication. Static split-inference methods use fixed partitio...

Feed lens

eval

Read the original at arxiv.org →Open in live feed Read that day’s brief

Joint Quantization and Dynamic Partitioning for Context-Aware Edge Vision Transformers

Earlier in this thread 4 items

LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers

RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models

MatMoE: Matryoshka Mixture-of-Experts with Dynamic Mixed-Precision Quantization for Efficient Inference

Coordinated Mixed-Precision KV Cache Quantization for Efficient LLM-based Multi-agent Systems