TRACE: Transformer Residual Activation Codebook Encoding for Communication-efficient Distributed Edge Inference
arXiv:2610.22435v1 Announce Type: new Abstract: Distributed Transformer inference across co-located edge devices is fundamentally communication-bound, as exchanging activations between sequence-parallel partitions dominates inference latency under commodity edge bandwidths. Existing compression sch…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-19 04:00 · arXiv cs.LG
TRACE: Transformer Residual Activation Codebook Encoding for Communication-efficient Distributed Edge Inference