DeepSpec
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
About this project
DeepSpec 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. Environment Install the Python dependencies: Data preparation additionally requires an inference engine to serve the target model when regenerating answers; see scripts/data/README.md for details. Workflow Run the stages in order — each stage's output feeds the next: 1. Data Preparation — download prompts, regenerate target answers, and build the target cache. 2. Training — train a draft model against the cached target outputs. 3. Evaluation — measure…
Technologies
Project health
GitHub
Reviews
Built by
Maintain deepseek-ai/DeepSpec? Claiming verifies admin access through your GitHub account and gives you control of this listing.
