The paper investigates whether per‑frame early exit can improve compute‑matched performance for on‑device speech enhancement. By supervising every intermediate depth of a causal model and fine‑tuning output heads, the authors produce a family of static models that are more Pareto‑efficient than those trained from scratch, achieving up to 0.11 higher PESQ for equivalent compute and matching the best PESQ at 30% less compute. After int8 quantization, the dynamic enhancer performs on the same latency‑quality frontier as static models on an STM32N6 microcontroller, with the policy execution adding only 26 µs per frame and a 2.2% latency overhead from graph splitting.
By Cl\'ement Laroche, Riccardo Miccini
arXiv:2512. 22420v5 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel.
By Rui Li, Zhaoning Zhang, Libo Zhang, Huaimin Wang, Xiang Fu, Zhiquan Lai
GEPARD is a streaming text‑to‑speech model that uses a standard large language model backbone to generate speech autoregressively, decoding audio with an FSQ‑based neural codec. It streams audio chunk‑by‑chunk as text arrives, achieving a real‑time factor of about 0.067 and an aggregate speedup of roughly 204× on a single GPU with 256 concurrent streams. The design keeps all complex auxiliary mechanisms outside the decode loop, enabling deployment with a standard LLM engine (vLLM) without kernel modifications.
By Denis Pavlov, Ulanbek Abdurazakov, Nursultan Bakashov
arXiv:2606. 00516v1 Announce Type: new Abstract: Mixed batching (MB)--interleaving prefill and decode in a single batch--has become the standard scheduling strategy for large language model (LLM) inference due to its efficiency in maximizing compute and memory utilization.
By Weifang Zhang, Yuzhou Nie, Bowen Pang, Guangrui Ma, Shining Wu
arXiv:2608. 06557v1 Announce Type: cross Abstract: The reasoning and agentic capabilities of large language models have expanded the range of applications they support, from short interactive exchanges to long, compute-heavy requests.
By Muhammad Adnan, Rohan Mahapatra, Prashant J. Nair, Daniel Berger, Pantea Zardoshti, Rodrigo Fonseca, Esha Choukse
arXiv:2608.22704v1 Announce Type: new
Abstract: Long-form audio inputs make the KV cache the dominant memory cost of speech LLMs. Prefill-only KV compression methods permanently discard audio KV posi...
By Yiming Yao, Chenyang Lyu, Xuanfan Ni, Longyue Wang, Weihua Luo, Yazheng Yang, Jinsong Su
arXiv:2606. 01839v1 Announce Type: cross Abstract: LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when the task arrives.
By Jianru Ding, Ryien Hosseini, Pouya Mahdi Gholami, Mingyuan Xiang, Henry Hoffmann
Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation. Their bidirectional attention prevents exact autoregressive-style KV caching, since committing one position shifts the KV activations of all others.
arXiv:2606. 02964v1 Announce Type: cross Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation.
By Chunan Shi, Yilei Chen, Yilin Chen, Xupeng Miao, Bin Cui
arXiv:2607. 16184v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) is a popular class of large language models (LLMs), offering high efficiency and accuracy.
By Yuchen Yang, Yifan Zhao, Anisha Dasgupta, Sasa Misailovic
HeadWiseKV is a training‑free framework that compresses the residual global key–value caches of hybrid long‑context language models by assigning each physical KV head a static, multilevel history window. It formulates cache allocation as a restricted operational rate–distortion problem and uses the SeqCalib algorithm to generate per‑head residency policies that account for interactions across layers. In evaluations on four hybrid models, HeadWiseKV preserves near‑full‑KV quality while reducing peak device memory usage by 8.59% at a 112K context length and extending the largest verified context from 114K to 161K.
By Renjie Xie, Juncheng Yang, Aoting Hu, Mingxi Zhang, Liyao Wu, Zheheng Hong, Wei Xu
arXiv:2606. 06302v2 Announce Type: replace Abstract: Multi-turn LLM serving accumulates dialogue history whose Key-Value (KV) cache grows with every turn and every user, quickly exceeding the model weights themselves and making memory -- not compute -- the binding constraint on throughput.
By Hyungmin Kim, Minsoo Kim, Hongseok Kim, Jungwook Choi