arXiv:2509. 04827v3 Announce Type: replace-cross Abstract: The energy cost of Large Language Model (LLM) inference is rapidly becoming a barrier to sustainable and scalable deployment.
arXiv:2606. 17104v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in latency- and cost-sensitive settings, inference efficiency has become a central systems challenge.
arXiv:2608.28044v1 Announce Type: cross Abstract: Large language model (LLM) inference serving is priced by tokens, but GPU energy is consumed over inference windows. This accounting mismatch makes t...
arXiv:2605. 23057v2 Announce Type: replace Abstract: RequestRouter is a lightweight request-boundary controller for reducing the latency and energy cost of single-GPU large language model inference.
arXiv:2605. 21312v2 Announce Type: replace-cross Abstract: Modern LLM serving is no longer homogeneous or monolithic.
arXiv:2609.09662v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) directly on mobile platforms at the edge is gaining traction due to a myriad of benefits, such as increased pr...
arXiv:2607. 05933v1 Announce Type: cross Abstract: Dynamic Voltage Frequency Scaling (DVFS) on resource-constrained embedded GPU platforms is essential for energy-efficient small language model (SLM) fine-tuning, as privacy- and personalization-driven adaptation increasingly requires local execution and involves repeated forward-backward optimization over many mini-batches, making it substantially more time- and energy-intensive than single-pass inference.
arXiv:2607. 09172v1 Announce Type: cross Abstract: Large Language Models are reshaping how software is developed and maintained.
The paper introduces a phase‑decoupled, model‑calibrated power controller for disaggregated large‑language‑model (LLM) serving, addressing the mismatch between GPU power settings and the distinct hardware regimes of prefill and decode stages. By calibrating separate power caps for each lane based on measured throughput‑latency cliffs, the authors achieve a 20.4% increase in tokens per joule with only a 3.5% rise in mean end‑to‑end latency on an 8‑node B200 cluster, outperforming NVIDIA’s Max‑Q profile. The approach also demonstrates consistent meeting of ITL‑p99 service‑level objectives across multiple MoE models and yields a 32.3% electricity savings over a sustained three‑day run.
arXiv:2606. 23001v1 Announce Type: cross Abstract: On-device LLM inference is increasingly attractive for privacy-preserving, reliable, and cost-effective deployment, yet its energy and thermal costs remain a critical bottleneck.
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.
The paper evaluates NVIDIA’s Max‑Q inference profile on a disaggregated B200 GPU system for large language model (LLM) serving, finding modest gains (+8.6% tokens/J) but increased latency (+5.2%). It proposes a phase‑decoupled, model‑calibrated power controller that sets a latency‑guaranteed SM‑clock window for prefill and a calibrated power cap for decode, achieving a 20.4% tokens/J improvement with only a 3.5% latency increase on an 8‑node Qwen3‑Coder‑480B deployment. The approach outperforms vendor profiles on both energy and latency, and demonstrates significant long‑term electricity savings in MoE‑based serving.
GroupKV is a lightweight hierarchical KV cache management system designed for long‑context diffusion large language model (dLLM) inference. It partitions the context into contiguous groups and uses coarse‑to‑fine sparse selection, cross‑layer consistency for predictive prefetching, and a staleness correction mechanism to keep the cache coherent amid dynamic KV updates. The approach also incorporates streaming prefill to lower peak memory usage, achieving up to 48× longer serviceable context, 3.73× faster inference in offload‑based settings, and competitive task accuracy.