diffusion drafters
PulseAugur coverage of diffusion drafters — every cluster mentioning diffusion drafters across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Split-KV method boosts diffusion drafter training efficiency
Researchers have developed Split-KV, a novel context parallelism method designed to enhance the training efficiency of diffusion drafters. This technique addresses the challenge of load balancing in diffusion drafters, …
-
XPress enhances speculative decoding for diffusion models
Researchers have developed xPress, a novel method to improve speculative decoding in diffusion drafters. This technique addresses the issue of independently sampled tokens in diffusion models, which can lead to jointly …
-
New research enhances LLM inference speed with advanced speculative decoding techniques · 8 sources tracked
Researchers are exploring advanced techniques to accelerate large language model (LLM) inference through speculative decoding. New methods like "Functional Reconstruction" aim to improve the agreement between draft and …