SPECTRE achieves up to 2.28x speedup for large-model LLM serving by running speculative draft generation and target verification in parallel using idle tail-model services.
Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
DeepSeekMath 7B reaches 51.7% on MATH via continued pretraining on curated web math data and Group Relative Policy Optimization.
N-gram draft models give larger and more consistent speed-ups for multilingual speculative decoding than fine-tuned neural drafts, despite lower acceptance rates, across translation and story generation.
PipeSD is a cloud-edge collaborative inference framework that overlaps token generation and communication via dynamic programming pipeline scheduling and uses Bayesian-optimized dual-threshold NAV triggering, delivering 1.16x-2.16x speedup and 14.3%-25.3% energy reduction over baselines.
citing papers explorer
-
SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference
SPECTRE achieves up to 2.28x speedup for large-model LLM serving by running speculative draft generation and target verification in parallel using idle tail-model services.