DeepSpec is a full-stack codebase for training and evaluating draft models for speculative decoding. It contains data preparation utilities, draft model implementations, training code, and evaluation scripts.
功能特性
- target_name_or_path — the target model the draft was trained against (e.g. Qwen/Qwen3-4B),
- draft_name_or_path — the draft checkpoint, e.g. ~/checkpoints/deepspec/dspark_block7_qwen3_4b/step_latest, or one of the Hugging Face repo IDs listed in Released Checkpoints.
- DFlash (MIT) — the DFlash draft-model design and training recipe.
- Qwen3 and Gemma — the target model families supported in this repo.