FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
Paper
•
2502.14856
•
Published
•
8
Speculative Decoding
-
-
From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens
Paper • 2502.18890 • Published • 30 -
DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting
Paper • 2503.00784 • Published • 13 -
Scaling Speculative Decoding with Lookahead Reasoning
Paper • 2506.19830 • Published • 12