OraCore · Topic ·research

SpecKV tunes speculative decoding on the fly

SpecKV adapts speculative decoding’s token budget per step, using draft-model signals to beat fixed gamma across compression settings.

1 articles in this thread ·Last updated 19h ago·First seen Jul 5, 2026

Timeline

  1. SpecKV adapts speculative decoding’s token budget per step, using draft-model signals to beat fixed gamma across compression settings.