AsymSpec speeds cloud-edge speculative decoding by uploading only token-probability pairs, moving correction traffic to the downlink, and overlapping independent requests instead of same-request runahead.
Fast inference from transform- ers via speculative decoding,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.DC 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric Networks
AsymSpec speeds cloud-edge speculative decoding by uploading only token-probability pairs, moving correction traffic to the downlink, and overlapping independent requests instead of same-request runahead.