├── LICENSE ├── README.md ├── assets ├── intro.png └── ssd_logo.png ├── decoding.py ├── evaluate.ipynb ├── evaluate_code.ipynb ├── evaluate_sum.ipynb ├── modeling_llama.py ├── search.ipynb ├── searching.py ├── skip_layers.json └── ssd.yml /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/README.md -------------------------------------------------------------------------------- /assets/intro.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/assets/intro.png -------------------------------------------------------------------------------- /assets/ssd_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/assets/ssd_logo.png -------------------------------------------------------------------------------- /decoding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/decoding.py -------------------------------------------------------------------------------- /evaluate.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/evaluate.ipynb -------------------------------------------------------------------------------- /evaluate_code.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/evaluate_code.ipynb -------------------------------------------------------------------------------- /evaluate_sum.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/evaluate_sum.ipynb -------------------------------------------------------------------------------- /modeling_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/modeling_llama.py -------------------------------------------------------------------------------- /search.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/search.ipynb -------------------------------------------------------------------------------- /searching.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/searching.py -------------------------------------------------------------------------------- /skip_layers.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/skip_layers.json -------------------------------------------------------------------------------- /ssd.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dilab-zju/self-speculative-decoding/HEAD/ssd.yml --------------------------------------------------------------------------------