Vibe Coding Discover

Use Cases

Multi-gpu Distributed Draft Model Training

Published projects tagged with this use case.

1 project

DeepSpec

★ 7.2K

DeepSpec is a full-stack Python codebase for training and evaluating speculative-decoding draft models (DSpark, DFlash, Eagle3) against targets like Qwen3 and Gemma. It covers data prep, 8-GPU training, and benchmark evaluation, plus released checkpoints.

AI Frameworks | Python · speculative-decoding · llm-inference

View Project →