LLM Inference Efficiency

LLM: Large Language Model

Overview

The field studies how to serve large language models faster and more cheaply while preserving answer quality, especially for long contexts, reasoning, and multi-step agents. Systems approaches improve batching, scheduling, speculative decoding, and key-value cache storage through methods such as quantization, eviction, and reuse. Model-side approaches adapt reasoning budgets, route queries between models, and compress prompts or context to avoid unnecessary computation. A central challenge is that gains depend on the model, workload, hardware, and latency or energy goals, so evaluations increasingly compare quality, cost, latency, and energy together on tasks such as LongBench, GSM8K, and MATH.

Latest papers

368 papers17 papers in the last four weeks, down 67% on the four weeks before. 0.1% of all new papers.

Jan 8, 2026

Nalar: Workflow-Aware Management of Agentic Applications

LLM-driven agentic applications automate complex, multi-step tasks, but serving them efficiently remains difficult due to heterogeneous components, dynamic model-driven control flow, long-lived state, and highly variable latencies. Nalar is a serving framework for agent workflows that separates workflow specification from execution while providing the runtime visibility and control needed for robust performance. Nalar preserves ordinary Python interfaces and control flow through lightweight auto-generated stubs that turn agent and tool invocations into futures carrying dependency and execution-context metadata. A two-level control architecture combines global policy computation with local event-driven enforcement to support adaptive routing, scheduling, and resource management across evolving workflows. A workflow-aware KV-cache layer enables the runtime to manage cache placement and lifetime. Together, these mechanisms enable scalable, efficient, policy-driven serving of heterogeneous agentic applications without burdening developers with orchestration logic. Across three agentic workloads, Nalar reduces tail latency by 34-74% and achieves up to 3.38x speedups.
Dec 16, 2025

Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring

The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that LRMs are still inefficient, over-generating verification and reflection steps. To address this challenge, we introduce the Step-Tagging framework, a lightweight sentence-classifier enabling real-time annotation of the type of reasoning steps that an LRM is generating. To monitor reasoning behaviors, we introduced ReasonType: a novel taxonomy of reasoning steps. Building on this framework, we demonstrated that online monitoring of the count of specific steps can produce effective interpretable early stopping criteria of LRM inferences. We evaluate the Step-tagging framework on three open-source reasoning models across standard benchmark datasets: MATH500, GSM8K, AIME and non-mathematical tasks (GPQA and MMLU-Pro). We achieve 20 to 50% token reduction while maintaining comparable accuracy to standard generation, with largest gains observed on more computation-heavy tasks. This work offers a novel way to increase control over the generation of LRMs, and a new tool to study behaviors of LRMs.
Nov 11, 2025

Intelligence per Watt: Measuring Intelligence Efficiency of Local AI

Large language model (LLM) queries are predominantly processed by frontier models in centralized cloud infrastructure. Demand growth strains this paradigm faster than providers can scale. Two advances create an opportunity to rethink it: small, local LMs (<=20B active parameters) now achieve competitive performance to frontier models on many tasks, and local accelerators (e.g., Apple M4 Max) can host these models at interactive latencies. This raises the question: can local inference viably redistribute demand from centralized infrastructure? This requires measuring both whether local LMs can accurately answer real-world queries and whether they can do so efficiently on power-constrained devices (e.g., laptops). We propose intelligence per watt (IPW), task accuracy per unit of power, as a unified metric for the capability and efficiency of local inference across model-accelerator configurations. We evaluate 20+ state-of-the-art local LMs, 8 hardware accelerators (local and cloud), and 1M real-world single-turn chat and reasoning queries. For each query, we measure accuracy (local LM win rate against frontier models), energy, latency, and power. We find three key results. First, local LMs successfully answer 88.7% of these queries, with accuracy varying by domain. Second, longitudinal analysis from 2023-2025 shows IPW improved 5.3x, driven by both algorithmic and accelerator advances, with locally-serviceable query coverage rising from 23.2% to 71.3%. Third, local accelerators achieve at least 1.4x lower IPW than cloud accelerators running identical models, revealing significant headroom for local accelerator optimization. These findings demonstrate that local inference can meaningfully redistribute demand from centralized infrastructure for a substantial subset of queries, with IPW serving as the critical metric for tracking this transition.
Sep 28, 2025

Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm

Many LLMs plan before they act, yet planning and execution are often still entangled in one long generation trace, enforced only through prompts, or split across separate components. We argue that these two stages call for different computation: planning benefits from diversity and breadth, whereas execution demands precision and faithful adherence to a chosen strategy. Treating them as a single undifferentiated chain wastes tokens on routine derivation and makes it costly to explore alternative strategies at test time. We present the Explore-Execute Chain (E\textsuperscript{2}C), which keeps both stages in one model but separates them structurally: a stochastic Exploration phase drafts a concise high-level plan, and a deterministic Execution phase carries it out. Causal SFT and RL train this split so that exploration stays informative and execution remains plan-faithful. Once plans are short yet decisive, extra inference compute can be directed to exploration rather than to repeatedly decoding full solutions. On AIME'2024 at K=32K{=}32, E\textsuperscript{2}C-ReAct Loop reaches 53.3% accuracy with only 12.4k tokens, outperforming Tree-of-Thoughts (N=32N{=}32: 50.0%, 71.3k). The same structure also supports lightweight domain adaptation: Exploration-Focused SFT (EF-SFT) updates only the planning phase, uses 3.5% of the tokens required by standard SFT, and improves medical benchmark accuracy by up to 14.5%.
Sep 8, 2025

JigSLO: Solving the Resource Puzzle for Efficient Multi-LLM Serving

GPU spatial sharing co-locates instances with complementary demands, such as compute-bound prefill and memory-bound decode, promising cost-efficient multi-LLM serving. Prior systems partition compute and coordinate shared memory capacity, but do not model bandwidth contention among co-located instances of heterogeneous LLMs. This contention makes each instance's latency depend on the memory-access patterns of its co-runners, even when its own resource allocation remains unchanged. Drawing on extensive measurements, we find that the latency impact of bandwidth contention can be captured by a time-shared memory-access model with contended and uncontended periods, so the overall latency can be analytically estimated as a time-weighted average of the latency estimates for these periods. We propose JigSLO, a contention-aware multi-LLM serving system that manages memory resources and schedules each model's prefill and decode phases as separate instances, treating their co-location as a placement decision. Its contention-aware predictor estimates per-instance latency under any co-location from standalone profiles alone. Guided by these predictions, its placement algorithm jointly selects each instance's tensor parallelism, compute share, and batch configuration, pairing complementary memory-access patterns to maximize throughput within each model's latency targets. JigSLO's shared resource manager complements this on the capacity side, sharing weights, pooling KV cache, and transferring it between prefill and decode instances. Across three datasets covering chat, code generation, and long-context summarization, JigSLO outperforms state-of-the-art baselines by 2.3×2.3\times in SLO attainment and 1.2×1.2\times in throughput on average, matching their best attainment with half the GPUs on long-context workloads.
May 22, 2025

EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning

Large Language Models (LLMs) excel at complex reasoning through search algorithms, yet current strategies often suffer from massive token consumption due to redundant exploration of semantically equivalent steps. Existing semantic similarity methods struggle to accurately identify such equivalence in domain-specific contexts like mathematical reasoning. To address this, we propose EquivPruner, a simple yet effective approach that identifies and prunes semantically equivalent actions during LLM reasoning search. We also introduce MathEquiv, the first dataset we created for mathematical statement equivalence, which enables the training of a lightweight equivalence detector. Extensive experiments across various models and tasks demonstrate that EquivPruner significantly reduces token consumption, improving searching efficiency and often bolstering reasoning accuracy. For instance, when applied to Qwen2.5-Math-7B-Instruct on GSM8K, EquivPruner reduced token consumption by 48.1% while also improving accuracy. Our code is available at https://github.com/Lolo1222/EquivPruner.
Mar 31, 2025

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (System 1) to slow and deep reasoning (System 2). While System 2 reasoning improves task accuracy, it often incurs substantial computational costs due to its slow thinking nature and inefficient or unnecessary reasoning behaviors. In contrast, System 1 reasoning is computationally efficient but leads to suboptimal performance. Consequently, it is critical to balance the trade-off between performance (benefits) and computational costs (budgets), giving rise to the concept of reasoning economy. In this survey, we provide a comprehensive analysis of reasoning economy in both the post-training and test-time inference stages of LLMs, encompassing i) the cause of reasoning inefficiency, ii) behavior analysis of different reasoning patterns, and iii) potential solutions to achieve reasoning economy. By offering actionable insights and highlighting open challenges, we aim to shed light on strategies for improving the reasoning economy of LLMs, thereby serving as a valuable resource for advancing research in this evolving area. We also provide a public repository to continually track developments in this fast-evolving field.
Nov 12, 2024

Saving GPU Hours in LLM Inference System Development and Online Workloads with Simulation and DBMS-Inspired Cache Replacement Policies

LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources. While LLM inference systems are capable of serving millions of requests from multiple users, they often lack theoretical models to determine whether they achieve the performance upper bounds of underlying hardware resources. Beyond online workload serving, merely analyzing existing systems-or developing yet another one-is both GPU-intensive and labor-intensive. This paper provides a comprehensive survey of LLM inference systems, focusing on their cache management policies and availability. We then show that simulations can be an effective tool to save GPU hours in the development and analysis phase of inference systems, revealing useful insights for developing better inference techniques, unlike how existing studies used simulations to find the best parameters inside a given system. Finally, we provide theoretical tools to estimate the optimal performance and formulate new ideas. Based on the theoretical analysis, especially on the cache management in LLM inference, we propose a simple yet effective cache replacement policy that can be easily plugged into existing preemptive schedulers and systems. We show that such a simple policy inspired from database systems can substantially save GPU hours in actual inference systems on online workloads. We share our experience submitting a journal paper to a database venue in November 2025 for anyone considering a similar path.