arXiv:2608. 03447v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive generation by verifying a draft block with a target model in parallel.
arXiv:2607. 12422v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive language model inference by using a cheap drafter to propose multiple future tokens and a target model to verify them.
arXiv:2607. 21535v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel.
Speculative decoding accelerates autoregressive language model inference by using a cheap drafter to propose multiple future tokens and a target model to verify them. A common design goal is therefore to improve draft quality while reducing auxiliary parameters and systems overhead.
Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel. Frontier models increasingly ship a built-in Multi-Token-Prediction (MTP/NEXTN) draft head under the assumption that the draft is negligibly cheap.
arXiv:2607. 24434v1 Announce Type: cross Abstract: Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory.
arXiv:2607. 05147v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification.
arXiv:2608. 03839v1 Announce Type: new Abstract: Training-free speculative decoding drafts by matching an exact suffix of the context against a pool of earlier context.
arXiv:2606. 00487v1 Announce Type: new Abstract: Using a diffusion model for parallel drafting is a promising approach for speculative decoding.
Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU.
arXiv:2606. 18967v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a representative post-training paradigm for LLMs, enabling strong reasoning and agentic capabilities.
arXiv:2608. 02989v1 Announce Type: new Abstract: Speculative decoding verifies a tree of draft tokens in one target-model forward pass.
arXiv:2607. 13124v1 Announce Type: cross Abstract: Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compressed checkpoints can collapse on the free-form generation that deployment actually requires.