Applying speculative decoding to secure two-party GPT inference, with a latency-insensitive multi-token forward and optimized private sampling, gives 2.1x to 6.0x speedups without changing the output distribution.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Efficient Private GPT Never Autoregressively Decodes
Applying speculative decoding to secure two-party GPT inference, with a latency-insensitive multi-token forward and optimized private sampling, gives 2.1x to 6.0x speedups without changing the output distribution.