arXiv Machine Learning
H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 1
Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache
arXiv:2608.30252v1 Announce Type: new Abstract: Long-context LLM applications such as document summarization and multi-turn agents require generation from prefixes spanning tens of thousands of token...
Hugging Face Trending Papers
Aug 31
Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache
Long-context LLM applications such as document summarization and multi-turn agents require generation from prefixes spanning tens of thousands of tokens, making decoding latency a major bottleneck. Sp...
arXiv AI
Jun 16
Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving
arXiv:2512. 22420v5 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel.
arXiv AI
Jun 2
MineDraft: A Framework for Batch Parallel Speculative Decoding
arXiv:2603. 18016v2 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to propose draft tokens that are subsequently verified by a larger target model.
arXiv AI
Jul 7
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
arXiv:2607. 05147v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification.
arXiv Machine Learning
6d ago
ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference
ASPIRE introduces a non‑synchronized batched self‑speculative decoding framework for long‑context LLM inference, addressing the memory bottleneck of attention by drafting tokens with sparse attention and verifying them with full attention. It combines a unified mixed forward pass, a lightweight online speculation scheduler that lets each request independently decide when to verify, and an intra‑draft refresh layer that updates the sparse context at every draft step. Experiments on three models and five benchmarks show 1.70–4.58× speedup over autoregressive baselines and a 27% average improvement over the strongest prior self‑speculative methods.