End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference

• URL: http://arxiv.org/abs/2606.27743v1
• Date: Fri, 26 Jun 2026 05:48:21 GMT
• Title: End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference
• Abstract summary: Large Language Models (LLMs) inference is typically deployed under a static resource assumption.<n>We propose Learning to Allocate (L2A), an end-to-end framework for resource-adaptive inference.
• Score: 40.35003253838957
• License: http://creativecommons.org/licenses/by/4.0/
• 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. However, real-world cloud infrastructure is inherently dynamic, characterized by fluctuating availability (e.g., spot instance preemption) and tiered Quality-of-Service requirements. In such volatile settings, static models are inflexible: they either crash under resource constraints or waste compute on redundant operations. To bridge this gap, we propose Learning to Allocate (L2A), an end-to-end framework for resource-adaptive inference. Unlike prior methods that condition only on input difficulty, we formulate inference as a constrained allocation problem conditioned on both the input and the runtime resource budget itself. We introduce lightweight, budget-conditioned and input-aware gating networks integrated into the LLM. These gates are trained via a unified objective that jointly optimizes task performance, logical consistency, and resource costs along three axes matching how real-world dynamics manifest: layer skipping for memory and depth pressure, head pruning for throughput contention, and reasoning-token reduction for latency tightening. This lets the model learn a budget-aware policy beyond input difficulty alone: it adaptively configures its computational footprint with respect to real-time resource dynamics, maximizing reasoning depth when resources permit while enforcing strict frugality when budgets tighten. A single L2A model traces the entire compute-accuracy Pareto frontier on Llama-3-8B and Qwen-3-4B: at up to 34% realized layer sparsity, it stays within 0.6% of the dense baseline on GSM8K, with the same gap holding zero-shot on out-of-distribution tasks, while every static or heuristic baseline requires a separately tuned model and still drops by 5-10% at comparable inference time.

Related papers

• Adaptive Error Budget Allocation for Fault-Tolerant Quantum Resource Estimation: A Metaheuristic Approach [0.14323566945483496]
  System-level resource estimation is a key component of fault-tolerant quantum computing toolchains.<n>We propose a training-free optimization framework that performs derivative-free search directly on the Azure Quantum Resource Estor.<n>We evaluate our framework across 433 circuits spanning 2 to 91 qubits from 31 families in the MQT Bench.
  arXiv  Detail & Related papers  (2026-08-16T07:14:29Z)
• Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL [0.8546394944138487]
  We formalize text-based world modeling as a steerable transition-dynamics problem decomposed into initial state.<n>We curate 239,403 grounded state-action trajectories spanning nine open-source environments and twelve frontier model families.<n>We introduce a plug-and-play GRPO training framework with deterministic state checks, and perform zero-shot transfer ablations on three OOD environments.
  arXiv  Detail & Related papers  (2026-05-07T00:40:32Z)
• Budgeted LoRA: Distillation as Structured Compute Allocation for Efficient Inference [6.886536285117155]
  Budgeted LoRA is a framework that treats model compression as a structured compute allocation problem.<n>We show that Budgeted LoRA matches standard LoRA perplexity at a moderate budget with a 1.74x compressed-module speedup.<n>It achieves a 4.05x speedup with moderate perplexity degradation, and it preserves higher accuracy on function-style in-context learning probes.
  arXiv  Detail & Related papers  (2026-05-05T22:59:14Z)
• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• Adaptive GPU Resource Allocation for Multi-Agent Collaborative Reasoning in Serverless Environments [0.3668877906130206]
  Multi-agent systems powered by large language models have emerged as a promising paradigm for solving complex reasoning tasks.<n> efficiently deploying these systems on serverless GPU platforms presents significant resource allocation challenges.<n>This paper presents an adaptive GPU resource allocation framework that achieves 85% latency reduction compared to round-robin scheduling.
  arXiv  Detail & Related papers  (2025-12-15T09:21:48Z)
• Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization [72.20212909644017]
  Deliberate Practice Policy Optimization (DPPO) is a metacognitive Metaloop'' training framework.<n>DPPO alternates between supervised fine-tuning (competence expansion) and reinforcement learning (skill refinement)<n> Empirically, training a vision-language embodied model with DPPO, referred to as Pelican-VL 1.0, yields a 20.3% performance improvement over the base model.<n>We are open-sourcing both the models and code, providing the first systematic framework that alleviates the data and resource bottleneck.
  arXiv  Detail & Related papers  (2025-11-20T17:58:04Z)
• A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning [40.6234318894435]
  Large language models split into two families: reasoning-centric LLMs and agentic LLMs.<n>This divide arises from fundamentally different training objectives, leading to mismatched strengths and inefficiency on simple queries.<n>We present Adaptive Agent Foundation Model (A$2$FM), a unified framework that follows a route-then-align principle.
  arXiv  Detail & Related papers  (2025-10-13T17:08:25Z)
• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints [1.00707850217229]
  Large language models (LLMs) are limited by substantial computational cost.<n>We introduce a "computational economics" framework that treats an LLM as an internal economy of resource-constrained agents.<n>We show that when computation is scarce, standard LLMs reallocate attention toward high-value tokens while preserving accuracy.
  arXiv  Detail & Related papers  (2025-08-14T07:55:45Z)
• Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models [14.321060805197874]
  Large Language Models (LLMs) deployed in real-world settings increasingly face the need to unlearn sensitive, outdated, or proprietary information.<n>Existing unlearning methods formulate forgetting and retention as a regularized trade-off, combining both objectives into a single scalarized loss.<n>We propose a new formulation of LLM unlearning as a constrained optimization problem: forgetting is enforced via a novel logit-margin flattening loss.
  arXiv  Detail & Related papers  (2025-06-05T17:55:23Z)
• Scalable Chain of Thoughts via Elastic Reasoning [61.75753924952059]
  Elastic Reasoning is a novel framework for scalable chain of thoughts.<n>It separates reasoning into two phases--thinking and solution--with independently allocated budgets.<n>Our approach produces more concise and efficient reasoning even in unconstrained settings.
  arXiv  Detail & Related papers  (2025-05-08T15:01:06Z)
• Resource Allocation via Model-Free Deep Learning in Free Space Optical Communications [119.81868223344173]
  The paper investigates the general problem of resource allocation for mitigating channel fading effects in Free Space Optical (FSO) communications. Under this framework, we propose two algorithms that solve FSO resource allocation problems.
  arXiv  Detail & Related papers  (2020-07-27T17:38:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.