Open access
Jul 2026
Runtime-Controlled Evaluation of Speculative Decoding Methods
SpecLLM, a pluggable evaluation framework that applies common scheduling, batching, KV-cache, CUDA Graph, and execution-backend policies across methods while preserving method-required proposal and verification paths, is presented.
Sungkyun Kim, Jaemin Kim, Yeongpil Cho et al.
· Electronics · 0 citations