cs.CLNov 18, 2026

NarrowSpec: Draft Hidden Width Need Not Match the Target in Speculative Decoding

Authors: Alagappan Valliappan, Ankit More, Dheevatsa Mudigere, Jatin Mitra

Organizations: NVIDIA

Abstract

Speculative decoding is widely used to speed up generation in large language models (LLMs), with a small draft model proposing tokens that one forward pass of the target model verifies. Draft models that read the target's hidden states, such as DFlash and EAGLE-3, typically inherit the target's hidden width. We show that the draft's whole residual stream can run at half or a quarter of that width while largely preserving acceptance. For DFlash, which borrows the target's vocabulary projection, the trained output adapter folds into it, giving one narrower projection with logits unchanged up to floating-point rounding. We test two drafter families, DFlash and EAGLE-3, on two targets, Qwen3-8B (NVFP4) and GPT-OSS-20B (MXFP4), in SGLang on a B200 and a DGX Spark (GB10). At batch size 1 and temperature 0, narrowing the draft to half or a quarter width speeds up end-to-end decoding by 1.06-1.12x on B200 and 1.13-1.44x on GB10. The speedup holds at larger batch sizes. From batch 32 to the largest batch each GPU fits, narrowing reaches up to 1.21x on both GPUs, and no narrow draft is slower than full width.

Figures & tables

Appendix figures & tables23 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding

    May 11, 2026Anton Plaksin, Sergei Krutikov, Sergei Skvortsov +1LLM CompressionSpeculative Decoding

  2. Give the Drafter a Second Chance to Guess: Parallel Reconsideration for Speculative Decoding

    Nov 3, 2026Hoang Anh Duy Le, Huibing Dong, Alireza Khadem +6Speculative DecodingLLM Inference Acceleration