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.
AdaptiveSD A Stability-Aware, Runtime-Adaptive Speculative Decoding Framework with Multi-Policy Orchestration for CPU-Constrained LLM Inference
arXiv:2607. 03876v1 Announce Type: new Abstract: With the rise of small quantized GGUF-based language models and their increasing use for on-device inference tasks, we have seen the growing need for an approach capable of reliably delivering these models at scale even under severe memory bandwidth constraints such as those imposed by pure CPU implementations.
Related stories
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 AI
Aug 12
MemSpec: Memory-Aware Runtime for Adaptive Draft Scheduling in Speculative Decoding on Edge Devices
arXiv:2608. 10362v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to speculate multiple tokens, reducing expensive target model decoding steps.
arXiv Machine Learning
Jun 18
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
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 Machine Learning
Sep 21
SpecQuant: Speculative Decoding with Multi-Parent Quantization for Adaptive LLM Inference
SpecQuant is a training‑free framework that merges speculative decoding with multi‑parent quantization to enable adaptive, efficient inference of large language models. It generates several quantized variants (INT4, FP8, FP16) from a single base model and routes queries to the appropriate variant based on predicted complexity, using lightweight models for simple tasks and full‑precision models for complex reasoning. Evaluations on Qwen2.5 models across MMLU, AlpacaEval, and GSM8K show 35‑43% speedups with less than 2% accuracy loss, facilitating practical on‑device LLM deployment without specialized infrastructure.
arXiv Machine Learning
Sep 17
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.
arXiv Machine Learning
Aug 5
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
arXiv:2602. 06932v5 Announce Type: replace Abstract: Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem.
arXiv AI
Sep 25
TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference
TIDE (Temporal Incremental Draft Engine) is a serving‑engine‑native framework that integrates online draft adaptation into high‑performance LLM inference. By reusing intermediate hidden states from the target model as training signals, TIDE avoids extra target model computation and serving‑time overhead, activating speculation and draft training only when beneficial. On heterogeneous GPU clusters, TIDE achieves up to 1.66× higher throughput than no‑speculation baselines, reduces training time by up to 3.02×, cuts storage needs by 24×, and improves system throughput by up to 1.22×.
arXiv Computation and Language
Sep 23
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
Flash-dLLM is a training‑free inference acceleration framework that improves the speed and memory efficiency of Diffusion Large Language Models (dLLMs). It tackles GPU memory I/O bottlenecks by introducing an I/O‑aware fused KV‑cache kernel and then employs a draft‑and‑verify decoding strategy that uses the dLLM itself as both drafter and verifier. Experiments on mathematical reasoning and code‑generation tasks show Flash‑dLLM outperforms existing acceleration methods, achieving up to 11.0× speedups over the Elastic‑Cache baseline.
arXiv Machine Learning
4d ago
Mira: Memory-Efficient MoE Inference Using Adaptive Caching and Predictive Expert Staging
arXiv:2609.38090v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-...
Hugging Face Trending Papers
Jul 27
DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference
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 AI
Jun 29
End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference
arXiv:2606. 27743v1 Announce Type: cross Abstract: Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment.