Speculative decoding accelerates generation by letting a lightweight drafter propose tokens for parallel verification by a target model. Diffusion drafters such as DFlash propose an entire token block in a single forward pass, but mainly focus on text-only tasks, leaving multimod…
⏱ Độ trễ thật của tab này: trung bình 7.2 giờ sau khi CVE được công bố (n = 5381, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
21
MMFlash: Faster Speculative Decoding for Vision-Language Models
🅲 hạng C
21
inclusionAI/ASpec
🧩 Chức năng: Công cụ quanh mô hình ngôn ngữ (prompt/agent)
A high-throughput training framework for Speculative decoding models.
🅲 hạng C
20
Multi-Future Drafting: Mixture Block Drafters for Tree-Verified Speculative Decoding
arXiv:2611.13017v1 Announce Type: new Abstract: Block drafters such as DFlash draft a block of future tokens in one forward pass, and draft trees such as DDTree verify the prefixes ranked highest by the product of the drafter's per-position distributions. Under tree verification…
🅲 hạng C