NarrowSpec: Draft Hidden Width Need Not Match the Target in Speculative Decoding
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.
Community
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.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- ChainFlow: Few-Step Latent Flow Matching for Speculative Decoding (2026)
- DForkTree: Accelerating Speculative Decoding with Fork-Aware Block Diffusion Draft Trees (2026)
- LoopSkim: Lossless Multi-Depth Speculative Decoding for Looped Language Models (2026)
- Only Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets (2026)
- TableTune: Measured, Self-Correcting Draft-Length Tables for Dynamic Speculative Decoding (2026)
- JetSpec++: Foresight Parallel Drafting with Self Refinements (2026)
- Sightline: Long-Window Speculative Decoding for Fast SVG Generation (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.23835 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper