DART

Official Implementation of DART (DART: Low-Latency Parallel Drafting with Continuity-Aware Tree Pruning for Speculative Decoding, EMNLP26).

What is DART?

Official Implementation of DART (DART: Low-Latency Parallel Drafting with Continuity-Aware Tree Pruning for Speculative Decoding, EMNLP26).