MARS fine-tunes autoregressive models to predict multiple tokens per step via continued training on instruction data, achieving 1.5-1.7x throughput while matching baseline accuracy and supporting real-time speed adjustment.
This incurs additional training cost: for the 0.5B model, AR SFT takes 15 H200-hours while MARS takes 33 H200-hours (2.2×); for the 7B model, 100 vs 202 H200-hours (2.0×)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MARS: Enabling Autoregressive Models Multi-Token Generation
MARS fine-tunes autoregressive models to predict multiple tokens per step via continued training on instruction data, achieving 1.5-1.7x throughput while matching baseline accuracy and supporting real-time speed adjustment.