draft model
An initial or preliminary version of a model that is not yet fully refined or validated, often serving as a basis for further development and testing.
- AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
- Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
- OmniDraft: A cross-vocabulary, online adaptive drafter for on-device speculative decoding
- SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding
- Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
- TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding
- ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding