2 papers
cs.ET2026
TableTune: Measured, Self-Correcting Draft-Length Tables for Dynamic Speculative Decoding
Abhishek Malvankar, Paul Castro, Nick Mitchell +1
Speculative decoding speeds up large language model (LLM) serving only while the GPU has spare compute, so the best draft length, the number of tokens a small drafter guesses per s…
cs.ET2026
WVA: A Global Optimization Control Plane for llmd
Abhishek Malvankar, Lionel Villard, Mohammed Abdi +6
As Large Language Models (LLMs) scale to handle massive concurrent traffic, optimizing the infrastructure required for inference has become a primary challenge. To manage the high…