LLM Inference Acceleration

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

108 papers in the last four weeks, up 120% on the four weeks before. 1.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 677

May 14, 2026cs.AI

Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling

Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling faces challenges in trade-off between sampling budget and reasoning quality. Current strategies remain inefficient as they typically treat sampling width and depth as orthogonal objectives, where width consensus methods risk reinforcing hallucinations, while depth pruning mechanisms prematurely truncate complex yet valid reasoning chains. Therefore, we propose Dual-Dimensional Consistency (DDC), a unified framework that bridges path quality with adaptive termination. By coupling Confidence-Weighted Bayesian protocol with a Trend-Aware Stratified Pruning, our method ensures that computational resources are concentrated on high quality reasoning paths, filtering hallucinations while accelerating consensus. Evaluations across five benchmarks demonstrate that this approach reduces token consumption by over 10 times while maintaining or exceeding the accuracy of strong baselines across various LLMs.

Rongman Xu, Yifei Li, Tianzhe Zhao +3

Xi’an Jiaotong University

Inference-Time Scaling LLM Inference Acceleration

May 14, 2026cs.LG

GQLA: Group-Query Latent Attention for Hardware-Adaptive Large Language Model Decoding

Multi-head Latent Attention (MLA), the attention used in DeepSeek-V2/V3, jointly compresses keys and values into a low-rank latent and matches the H100 roofline almost perfectly. Its trained weights, however, expose only one decoding path - an absorbed MQA form - which ties efficient inference to H100-class compute-bandwidth ratios, forfeits tensor parallelism along the head axis, and yields no Multi-Token Prediction (MTP) gain on commodity inference GPUs such as the export-restricted H20. We propose Group-Query Latent Attention (GQLA), a minimal modification of MLA whose trained weights expose two algebraically equivalent decoding paths over the same parameters: an MQA-absorb path identical to MLA's, and a GQA path with a per-group expanded cache. The runtime picks the path that matches the target hardware - no retraining, no custom kernels - so a single set of GQLA weights pins the rooflines of both H100 (MQA-absorb, s_q=1) and H20 (GQA + MTP, s_q=2), while supporting up to 8-way zero-redundancy tensor parallelism on the GQA path. To avoid pretraining from scratch we extend TransMLA into TransGQLA, which converts a pretrained GQA checkpoint into a GQLA model; on LLaMA-3-8B it compresses the per-token KV cache to 28.125% of the GQA baseline on the MQA-absorb path while structurally preserving GQA-level traffic on the per-group path.

Fanxu Meng

Institute for Artificial Intelligence, Peking University

Grouped-Query Attention GPU Acceleration Self-Attention Transformer Attention LLM Inference Acceleration KV-Cache Compression+2

May 14, 2026cs.CL

Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing

Speculative decoding accelerates LLM inference by having a lightweight draft model propose speculative windows of candidate tokens for parallel verification by a larger target model. In practice, speculative efficiency is often bottlenecked by hard-to-draft positions, where an early mismatch truncates the accepted prefix and invalidates the rest of the speculative window. Most learning-based drafters are still optimized with token-level supervised objectives, even though speculative utility is inherently window-level and prefix-sensitive. We propose PPOW (Performance-Driven Policy Optimization with Adaptive Windowing), a reinforcement learning framework that shifts drafter optimization from token-level imitation to window-level optimization. PPOW combines a Cost-Aware Speedup Reward, a Distribution-Based Proximity Reward, and Adaptive Divergence-Aware Windowing, which prioritizes informative windows with high confidence-weighted draft-target divergence. PPOW achieves average acceptance lengths of 6.29-6.52 and speedups of 3.39-4.36

\times

across multiple model families and benchmarks under a unified decoding protocol. These results show that performance-driven window-level optimization is a practical approach to improving speculative decoding efficiency.

Jie Jiang, Xing Sun, Ruotian Chen +2

Speculative Decoding LLM Inference Acceleration

May 14, 2026cs.LG

XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference

We introduce XFP, a dynamic weight quantizer for LLM inference that inverts the conventional workflow: the operator specifies reconstruction quality floors on per-channel cosine similarity (one strict floor for attention and shared experts, one lazy floor for routed-expert MoE); XFP determines codebook size, outlier budget, and packing per layer automatically -- no Hessian, no calibration data, no manual bit-width selection. Each weight matrix is decomposed into a sparse fp16 outlier residual and a dense sub-byte index tensor into a per-group learned codebook. Two storage modes share one auto-select frontend and one fused decode kernel: V2 (per-channel Lloyd) and V2a (shared library of L=32 codebooks per layer). On Qwen3.5-122B-A10B under V2, XFP reaches 138 tok/s single-stream decode on workstation hardware (RTX PRO 6000 Blackwell, TP=2) at 94.49% GSM8K strict-match (3 seeds, n=3957), and is 49% faster than Marlin INT4 at TP=1. For models that do not fit in the target memory envelope, we present the H-Process: a quality-driven iteration over the two cosine thresholds that finds the operating point at which the model just fits while still producing sensible output. Three constraints define its search space: the operator-set thresholds, an OOM boundary at quantize-on-load, and a garbage boundary in generation (cosine similarity steers; benches verify). On Qwen3.5-397B-A17B (512 routed experts/layer), the H-Process fits the full expert population into 2x96 GB at ~3.4 effective bits and delivers 100.9 tok/s long-output decode at 66.72% GSM8K strict-match on the full 1319-problem set (single seed at submission; multi-seed evaluation in progress), exceeding INT4 with routed-expert pruning on memory, throughput, and accuracy simultaneously.

Thomas Witt

Gemini Stiftung Leipzig

LLM Quantization Vector Quantization LLM Inference Acceleration Post-Training Quantization Neural Network Quantization

May 14, 2026cs.AI

BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE

Mixture-of-Experts (MoE) architectures enhance the efficiency of large language models by activating only a subset of experts per token. However, standard MoE employs a fixed Top-K routing strategy, leading to redundant computation and suboptimal inference latency. Existing acceleration methods either require costly retraining with architectural changes or suffer from severe performance drop at high sparsity due to train-inference mismatch. To address these limitations, we propose BEAM (Binary Expert Activation Masking), a novel method that learns token-adaptive expert selection via trainable binary masks. With a straight-through estimator and an auxiliary regularization loss, BEAM induces dynamic expert sparsity through end-to-end training while maintaining model capability. We further implement an efficient custom CUDA kernel for BEAM, ensuring seamless integration with the vLLM inference framework. Experiments show that BEAM retains over 98% of the original model's performance while reducing MoE layer FLOPs by up to 85%, achieving up to 2.5

\times

faster decoding and 1.4

\times

higher throughput, demonstrating its effectiveness as a practical, plug-and-play solution for efficient MoE inference.

Juntong Wu, Jialiang Cheng, Qishen Yin +5

Taobao & Tmall Group of Alibaba · Shenzhen Graduate School, Peking University

Sparse Mixture-of-Experts Mixture-of-Experts Inference LLM Inference Acceleration LLM Routing

May 14, 2026cs.LG

PreFT: Prefill-only finetuning for efficient inference

Large language models can now be personalised efficiently at scale using parameter efficient finetuning methods (PEFTs), but serving user-specific PEFTs harms throughput, even with specialised kernels and memory management techniques. This is because, theoretically and empirically, a mismatch exists between prefill (processing a large number of tokens at once) and decode (generating a single token autoregressively): the latter has far lower throughput when serving multiple adapters. Rather than optimising performance relative to parameter count, for efficient multi-adapter serving, we instead ought to optimise performance relative to serving throughput. We therefore propose PreFT (Prefill-only Finetuning), wherein we only apply the adapter to prefill tokens and discard it afterwards. PreFT significantly increases throughput with minimal effect on performance. We develop and release an efficient implementation of two prefill-only PEFTs, LoRA and ReFT, on the vLLM inference engine. We first show that serving multi-user PreFTs is more efficient than traditional PEFTs (

1.9\times

the throughput when serving

512

adapters on Llama 3.1 70B). Then, we compare the performance of prefill-only vs. all-token adapters on a variety of supervised finetuning and reinforcement learning tasks with LMs at varying scales. On SFT, we observe that the evaluation loss of PreFTs is higher than PEFTs, but can be compensated by increasing rank with nearly no reduction in throughput. On RL, we consistently find that PreFTs approach parity with standard PEFTs. Together, this work validates prefill-only adaptation of LLMs as a more favourable accuracy-throughput tradeoff than existing PEFTs for personalised serving.

Andrew Lanpouthakoun, Aryaman Arora, Zhengxuan Wu +4

Stanford University · Tilde Research

Fine-Tuning LLM Serving Adapter Tuning LLM Inference Acceleration Parameter-Efficient Fine-Tuning

May 13, 2026cs.AI

Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection

While synthetic data generation with large language models (LLMs) is widely used in post-training pipelines, existing approaches typically generate full outputs before applying quality filters, leading to substantial token waste on samples that are ultimately discarded. To address this, we propose Multi-Stage In-Flight Rejection (MSIFR), a lightweight, training-free framework that detects and terminates low-quality generation trajectories at intermediate checkpoints before they reach full completion. MSIFR decomposes the generation process into sequential stages and applies fast rule-based validators to identify arithmetic inconsistencies, hallucination patterns, and formatting violations, enabling early rejection of faulty samples. We formalize in-flight rejection as a sequential decision process and show that any non-trivial discard policy reduces expected token consumption, with stage-wise savings increasing when rejection occurs earlier in the generation pipeline. We further demonstrate that conditional utility estimates form a martingale, ensuring that early, in-flight rejection does not bias the expected utility of retained samples. Across five instruction-tuned models and seven reasoning benchmarks, MSIFR reduces token consumption by 11%-77% as a standalone method, and up to 78.2% when combined with early-exit methods, while preserving or improving evaluation accuracy. These results confirm that MSIFR provides a practical mechanism for improving the efficiency of LLM-based synthetic data generation without additional training or architectural changes.

Anjir Ahmed Chowdhury, Syed Zawad, Feng Yan

Department of Computer Science University of Houston · IBM Research

Synthetic Data Generation LLM Inference Acceleration Synthetic Data Generation for Language Models

May 13, 2026cs.LG

Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility

Under modern test-time compute and agentic paradigms, language models process ever-longer sequences. Efficient text generation with transformer architectures is increasingly constrained by the Key-Value cache memory footprint and bandwidth. To address this limitation, we introduce Self-Pruned Key-Value Attention (SP-KV), a mechanism designed to predict future KV utility in order to reduce the size of the long-term KV cache. This strategy operates at a fine granularity: a lightweight utility predictor scores each key-value pair, and while recent KVs are always available via a local window, older pairs are written in the cache and used in global attention only if their predicted utility surpasses a given threshold. The LLM and the utility predictor are trained jointly end-to-end exclusively through next-token prediction loss, and are adapted from pretrained LLM checkpoints. Rather than enforcing a fixed compression ratio, SP-KV performs dynamic sparsification: the mechanism adapts to the input and typically reduces the KV cache size by a factor of

3

to

10\times

, longer sequences often being more compressible. This leads to vast improvements in memory usage and decoding speed, with little to no degradation of validation loss nor performance on a broad set of downstream tasks. Beyond serving as an effective KV-cache reduction mechanism, our method reveals structured layer- and head-specific sparsity patterns that we can use to guide the design of hybrid local-global attention architectures.

Gergely Szilvasy, Manuel Faysse, Maria Lomeli +5

Meta FAIR · MICS, CentraleSupélec

Self-Attention KV Caching Long-Context Language Model Inference Memory-Efficient Optimization KV-Cache Management Transformer Attention+3

May 13, 2026cs.CL

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding

Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a target model in parallel. Its efficiency, however, critically depends on the average accepted length

τ

, i.e., how many draft tokens survive each verification step. In this work, we identify a new mechanism-level vulnerability in model-based speculative decoding: the drafter is trained to approximate the target model distribution, but this approximation is inevitably imperfect. Such a drafter-target mismatch creates a hidden attack surface where small perturbations can preserve the target model's visible behavior while substantially reducing draft-token acceptability. We propose Mistletoe, a stealthy acceleration-collapse attack against speculative decoding. Mistletoe directly targets the acceptance mechanism of speculative decoding. It jointly optimizes a degradation objective that decreases drafter-target agreement and a semantic-preservation objective that constrains the target model's output distribution. To resolve the conflict between these objectives, we introduce a null-space projection mechanism, where degradation gradients are projected away from the local semantic-preserving direction, suppressing draft acceptance while minimizing semantic drift. Experiments on various speculative decoding systems show that Mistletoe substantially reduces average accepted length

τ

, collapses speedup, and lowers averaged token throughput, while preserving output quality and perplexity. Our work highlights that speculative decoding introduces a mechanism-level attack surface beyond existing output robustness, calling for more robust designs of LLM acceleration systems.

Shuoyang Sun, Chang Dai, Hao Fang +6

Harbin Institute of Technology, Shenzhen · South China University of Technology · Tsinghua Shenzhen International Graduate School, Tsinghua University +1

Adversarial Attacks on LLMs Speculative Decoding LLM Security LLM Inference Acceleration

May 13, 2026cs.LG

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained policies are produced over a small number of expensive base-model deployments. Instead of materializing each policy as a merged full checkpoint, MinT keeps the base model resident and moves exported LoRA adapter revisions through rollout, update, export, evaluation, serving, and rollback, hiding distributed training, serving, scheduling, and data movement behind a service interface. MinT scales this path along three axes. Scale Up extends LoRA RL to frontier-scale dense and MoE architectures, including MLA and DSA attention paths, with training and serving validated beyond 1T total parameters. Scale Down moves only the exported LoRA adapter, which can be under 1% of base-model size in rank-1 settings; adapter-only handoff reduces the measured step by 18.3x on a 4B dense model and 2.85x on a 30B MoE, while concurrent multi-policy GRPO shortens wall time by 1.77x and 1.45x without raising peak memory. Scale Out separates durable policy addressability from CPU/GPU working sets: a tensor-parallel deployment supports 10^6-scale addressable catalogs (measured single-engine sweeps through 100K) and thousand-adapter active waves at cluster scale, with cold loading treated as scheduled service work and packed MoE LoRA tensors improving live engine loading by 8.5-8.7x. MinT thus manages million-scale LoRA policy catalogs while training and serving selected adapter revisions over shared 1T-class base models.

Mind Lab, :, Song Cao +60

LLM Serving Adapter Tuning Low-Rank Adaptation LLM Inference Acceleration

May 13, 2026stat.ML

Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference

Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplication has become a critical bottleneck on modern AI accelerators. On architectures with decoupled compute units (e.g., Ascend NPUs), dequantization operations can consume more cycles than the matrix multiplication itself, leaving the high-throughput tensor cores underutilized. This paper presents Multi-Scale Dequant (MSD), a quantization framework that removes weight/KV dequantization from the GEMM critical path. Instead of lifting low-bit weights to BF16 precision, MSD decomposes high-precision BF16 activations into multiple low-precision components, each of which can be multiplied directly with quantized weights via native hardware-accelerated GEMM. This approach shifts the computational paradigm from precision conversion to multi-scale approximation, avoiding INT8-to-BF16 weight conversion before GEMM. We instantiate MSD for two weight formats and derive tight error bounds for each. For INT8 weights (W4A16), two-pass INT8 decomposition achieves near 16 effective bits. For MXFP4 weights (W4A16), two-pass MXFP4 decomposition yields near 6.6 effective bits with error bound 1/64 per block surpassing single-pass MXFP8(5.24 bits) while maintaining the same effective GEMM compute time. We further derive closed-form latency and HBM traffic models showing that MSD avoids the Vector-Cube pipeline stall caused by dequantization and reduces KV cache HBM traffic by up to 2.5 times in attention. Numerical simulations on matrix multiplication and Flash Attention kernels confirm that MSD does not degrade accuracy compared to dequantization baselines, and in many settings achieves lower L2 error.

Lingchao Zheng, Yuwei Fan, Jun Li +5

Huawei

LLM Quantization LLM Inference Acceleration

May 13, 2026cs.LG

N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation

Improving the inference efficiency of autoregressive transformers typically means reducing FLOPs per token, usually through approximations that degrade model quality. We introduce N-vium, a mixture-of-exits transformer that partially parallelizes computation across depth on standard hardware, increasing effective FLOPs per second rather than minimizing compute per token. N-vium attaches prediction heads at multiple depths and defines the next-token distribution as a learned mixture over these exits, with token-adaptive routing. This formulation strictly generalizes the standard transformer, which is recovered exactly when routing assigns zero mass to all intermediate heads. Sampling from the mixture is exact, and complete KV caches are recovered by deferring the upper-layer computation and batching it with later tokens. We pretrain N-vium at scales up to 1.5B parameters. Our largest model reaches 57.9% wall-clock speedup over a parameter- and data-matched standard transformer at no perplexity cost.

Aleksander Lorenc, Frédéric Berdoz, Joël Mathys +1

ETH Zurich

Efficient Transformer Inference LLM Inference Acceleration Language Modeling

May 13, 2026cs.CL

STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes

Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking. This inefficiency is especially problematic in low-data fine-tuning regimes, where real applications adapt reasoning models with limited supervision and cannot rely on large-scale teacher distillation or heavy test-time control. To address this, we propose STOP (Structured On-policy Pruning), an on-policy algorithm for analyzing and pruning long-form reasoning traces. STOP constructs self-distilled traces from the model. Then it maps each trace into a structured reasoning interface through node segmentation, taxonomy annotation, and reasoning-tree construction. On top of this interface, we introduce ECN (Earliest Correct Node), which retains the shortest prefix ending at the earliest node. Experiments on DeepSeek-R1-Distill-Qwen-7B and DeepSeek-R1-Distill-LLaMA-3-8B across GSM8K, Math 500, and AIME 2024 show that STOP reduces generated tokens by 19.4% to 42.4% while largely preserving accuracy in low-data fine-tuning. Beyond efficiency, our analyses show that STOP induces much smaller distributional shift than teacher-guided pruning, improves the structural efficiency of generated reasoning, and reallocates reasoning effort away from redundant verification and backtracking toward more productive exploration.

Chenjun Xu, Zhennan Zhou, Zhan Su +3

University of Washington · University of Montreal

LLM Pruning LLM Fine-Tuning Efficient Language Model Reasoning LLM Inference Acceleration Structured Reasoning Large Reasoning Models+1

May 12, 2026cs.LG

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion

We introduce Orthrus, a simple and efficient dual-architecture framework that unifies the exact generation fidelity of autoregressive Large Language Models (LLMs) with the high-speed parallel token generation of diffusion models. The sequential nature of standard autoregressive decoding represents a fundamental bottleneck for high-throughput inference. While diffusion language models attempt to break this barrier via parallel generation, they suffer from significant performance degradation, high training costs, and a lack of rigorous convergence guarantees. Orthrus resolves this dichotomy natively. Designed to seamlessly integrate into existing Transformers, the framework augments a frozen LLM with a lightweight, trainable module to create a parallel diffusion view alongside the standard autoregressive view. In this unified system, both views attend to the exact same high-fidelity Key-Value (KV) cache; the autoregressive head executes context pre-filling to construct accurate KV representations, while the diffusion head executes parallel generation. By employing an exact consensus mechanism between the two views, Orthrus guarantees lossless inference, delivering up to a 7.8x speedup with only an O(1) memory cache overhead and minimal parameter additions.

Chien Van Nguyen, Chaitra Hegde, Van Cuong Pham +3

University of Oregon · Google DeepMind · Adobe Research

Language Model Decoding Diffusion Language Model Inference LLM Inference Acceleration Diffusion Language Model Decoding

May 12, 2026cs.LG

Search Your Block Floating Point Scales!

Quantization has emerged as a standard technique for accelerating inference for generative models by enabling faster low-precision computations and reduced memory transfers. Recently, GPU accelerators have added first-class support for microscaling Block Floating Point (BFP) formats. Standard BFP algorithms use a fixed scale based on the maximum magnitude of the block. We observe that this scale choice can be suboptimal with respect to quantization errors. In this work, we propose ScaleSearch, an alternative strategy for selecting these scale factors: using a fine-grained search leveraging the mantissa bits in microscaling formats to minimize the quantization error for the given distribution. ScaleSearch can be integrated with existing quantization methods such as Post Training Quantization and low-precision attention, and is shown to improve their performance. Additionally, we introduce ScaleSearchAttention, an accelerated NVFP4-based attention algorithm, which uses ScaleSearch and adapted prior techniques to ensure near-0 performance loss for causal language modeling. Experiments show that ScaleSearch reduces quantization error by 27% for NVFP4 and improves language model PTQ by up to 15 points for MATH500 (Qwen3-8B), while ScaleSearchAttention improves Wikitext-2 PPL by upto 0.77 points for Llama 3.1 70B. The proposed methods closely match baseline performance while providing quantization accuracy improvements.

Tanmaey Gupta, Hayden Prairie, Xiaoxia Wu +10

Cornell University, Ithaca, NY, USA · Together AI, USA · University of California San Diego, La Jolla, CA, USA +1

4-Bit Quantization LLM Inference Acceleration Post-Training Quantization Neural Network Quantization

May 12, 2026cs.LG

D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting

Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffusion-based parallel drafters such as DFlash predict the full B-token block in one forward pass, enabling deeper drafters and longer accepted blocks. However, existing multi-token drafter objectives often use fixed position-dependent weighting schedules, such as head-dependent weights or block-position decays, which do not adapt as the positions limiting acceptance change during training. To address this, we derive per-position training weights from a differentiable surrogate of expected accepted draft length, matching the weight of each position to its log-probability gradient contribution. The resulting loss, D-PACE (Dynamic Position-Aware Cross-Entropy), shifts training signal toward positions that currently limit acceptance as the drafter improves. Across six benchmarks, two Qwen3-4B draft depths, two decoding temperatures, and two additional target models, D-PACE consistently improves both wall-clock speedup and average emitted length, with 2.3% measured training-time overhead and no changes to the drafter architecture or inference procedure.

Tianyu Wu, Yu Yao, Zhenting Qi +7

1Harvard · 2MIT

Speculative Decoding LLM Inference Acceleration Parallel Decoding Diffusion Language Model Decoding

May 12, 2026cs.CL

Efficient LLM-based Advertising via Model Compression and Parallel Verification

Large language models (LLMs) have shown remarkable potential in advertising scenarios such as ad creative generation and targeted advertising. However, deploying LLMs in real-time advertising systems poses significant challenges due to their high inference latency and computational cost. In this paper, we propose an Efficient Generative Targeting framework that integrates adaptive group quantization, layer-adaptive hierarchical sparsification, and prefix-tree parallel verification to accelerate LLM inference while preserving generation quality. Extensive experiments on two real-world advertising scenarios demonstrate that our framework achieves significant speedup with acceptable quality degradation, making it operationally viable for practical deployments.

Wenxin Dong, Chang Gao, Guanghui Yu +9

Baidu Inc. Beijing, China

LLM Quantization LLM Compression Online Advertising LLM Inference Acceleration

May 12, 2026cs.CL

Ada-MK: Adaptive MegaKernel Optimization via Automated DAG-based Search for LLM Inference

When large language models (LLMs) serve real-time inference in commercial online advertising systems, end-to-end latency must be strictly bounded to the millisecond range. Yet every token generated during the decode phase triggers thousands of kernel launches, and kernel launch overhead alone can account for 14.6% of end-to-end inference time. MegaKernel eliminates launch overhead and inter-operator HBM round-trips by fusing multiple operators into a single persistent kernel. However, existing MegaKernel implementations face a fundamental tension between portability and efficiency on resource-constrained GPUs such as NVIDIA Ada: hand-tuned solutions are tightly coupled to specific architectures and lack portability, while auto-compiled approaches introduce runtime dynamic scheduling whose branch penalties are unacceptable in latency-critical settings. We observe that under a fixed deployment configuration, the optimal execution path of a MegaKernel is uniquely determined, and runtime dynamic decision-making can be entirely hoisted to compile time. Building on this insight, we propose Ada-MK: (1) a three-dimensional shared-memory constraint model combined with K-dimension splitting that reduces peak shared memory usage by 50%; (2) MLIR-based fine-grained DAG offline search that solidifies the optimal execution path, completely eliminating runtime branching; and (3) a heterogeneous hybrid inference engine that embeds MegaKernel as a plugin into TensorRT-LLM, combining high-throughput Prefill with low-latency Decode. On an NVIDIA L20, Ada-MK improves single-batch throughput by up to 23.6% over vanilla TensorRT-LLM and 50.2% over vLLM, achieving positive gains across all tested scenarios--the first industrial deployment of MegaKernel in a commercial online advertising system.

Wenxin Dong, Mingqing Hu, Guanghui Yu +7

Baidu Inc.

GPU Kernel Optimization GPU Acceleration LLM Inference Acceleration GPU Kernel Generation

May 12, 2026cs.CL

BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion

Autoregressive language models generate text one token at a time, yet natural language is inherently structured in multi-token units, including phrases, n-grams, and collocations that carry meaning jointly. This one-token bottleneck limits both the expressiveness of the model during pre-training and its throughput at inference time. Existing remedies such as speculative decoding or diffusion-based language models either leave the underlying bottleneck intact or sacrifice the causal structure essential to language modeling. We propose BitLM, a language model that represents each token as a fixed-length binary code and employs a lightweight diffusion head to denoise multiple tokens in parallel within each block. Crucially, BitLM preserves left-to-right causal attention across blocks while making joint lexical decisions within each block, combining the reliability of autoregressive modeling with the parallelism of iterative refinement. By replacing the large-vocabulary softmax with bitwise denoising, BitLM reframes token generation as iterative commitment in a compact binary space, enabling more efficient pre-training and substantially faster inference without altering the causal foundation that makes language models effective. Our results demonstrate that the one-token-at-a-time paradigm is not a fundamental requirement but an interface choice, and that changing it can yield a stronger and faster language model. We hope BitLM points toward a promising direction for next-generation language model architectures.

Shaobin Zhuang, Yuang Ai, Jiaming Han +7

Shanghai Jiao Tong University · MMLab, The Chinese University of Hong Kong · Institute of Automation, Chinese Academy of Sciences +1

Multi-Token Prediction Autoregressive Language Modeling LLM Inference Acceleration Diffusion Language Model Decoding Diffusion Language Models

May 12, 2026cs.LG

Fast MoE Inference via Predictive Prefetching and Expert Replication

The Mixture of Experts (MoE) architecture has become a fundamental building block in state-of-the-art large language models (LLMs), improving domain-specific expertise in LLMs and scaling model capacity without proportionally increasing their computational overhead. However, MoE inference often suffers from suboptimal GPU utilization, load imbalance, and elevated latency arising from multiple tokens waiting on the same experts for their computation which arises from sparsity of expert activation. To address these challenges, we propose a dynamic expert replication strategy that predicts which experts are likely to be overloaded and replicates them for upcoming batches of tokens. The replicated experts process batch tokens concurrently across layers, which leads to improved parallelism, shorter GPU idle time, and significantly faster inference. Experimental evaluations conducted on large-scale MoE models, including Switch-base-128 and Switch-base-256, demonstrate that our method achieves near-complete GPU utilization (approx 100%), leading to upto 3x improvement in inference speed while preserving approximately 90-95% of the performance of baseline architectures

Ankit Jyothish, Ali Jannesari, Aishwarya Sarkar +1

Iowa State University Ames, USA

Expert Load Balancing GPU Acceleration Mixture of Experts Mixture-of-Experts Inference LLM Inference Acceleration

May 11, 2026cs.LG

Block-Based Double Decoders

Encoder-decoder models offer substantial inference-time savings over decoder-only models, but their pretraining objectives suffer from sparse supervision and dynamic sequence lengths, keeping them out of practice at scale. We propose block-based double decoders, a novel transformer architecture that utilizes doubly-causal block-based attention masks to train with full loss supervision and static sequence packing, combining decoder-only training efficiency with encoder-decoder inference efficiency. In scaling law experiments, block-based double decoders strongly outperform encoder-decoders and closely track decoder-only models across scales. At inference time, they cut KV-cache memory and per-token compute by at least 2/3 without sacrificing prefill caching or other existing inference optimizations available to decoder-only models.

Asher Labovich, Benjamin Bradley, Vanessa Alexander +1

Department of Computer Science Brown University Providence, RI 02912

Efficient Transformer Inference LLM Inference Acceleration Attention Mechanisms

May 11, 2026cs.AI

Rethinking LLMOps for Fraud and AML: Building a Compliance-Grade LLM Serving Stack

Fraud detection and anti-money-laundering (AML) compliance are high-value domains for large language models (LLMs), but their serving requirements differ sharply from generic chat workloads. Compliance prompts are often prefix-heavy, schema-constrained, and evidence-rich, combining reusable policy instructions, risk taxonomies, transaction or document context, and short structured outputs such as JSON labels or risk factors. These properties make prefix reuse, KV-cache efficiency, runtime tuning, model orchestration, and output validation first-order systems concerns. This paper introduces a workload-aware LLMOps stack for fraud and AML workloads using self-hosted open-weight models such as Meta Llama and Alibaba Qwen. The stack combines vLLM-style runtime tuning, PagedAttention, Automatic Prefix Caching, multi-adapter serving, adapter and prompt-length-aware batching, sleep/wake lifecycle management, speculative decoding, and optional prefill/decode disaggregation. To avoid exposing institution-specific data, the reproducibility track converts public synthetic AML datasets, including IBM AML and SAML-D, into prefix-heavy compliance prompts with reusable policy text, transaction evidence, typology definitions, and schema-constrained outputs. We also incorporate an LLM-as-judge quality gate using deterministic compliance checks, reference metrics, expert-adjudicated calibration data where available, and multi-judge rubric scoring. Across public-synthetic AML workloads and controlled serving benchmarks, workload-aware tuning improved throughput from 612-650 to 3,600 requests/hour, reduced P99 latency from 31-38 seconds to 6.4-8.7 seconds, and increased GPU utilization from 12% to 78%. These results show that regulated LLM performance is a workload-design, serving-optimization, and quality-gating problem, not only a model-selection problem.

Prathamesh Vasudeo Naik, Naresh Dintakurthi, Yue Wang

LLM Serving Financial Fraud Detection LLM Inference Acceleration

May 11, 2026cs.LG

CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration

Auto-regressive decoding in Large Language Models (LLMs) is inherently memory-bound: every generation step requires loading the model weights and intermediate results from memory (e.g., High-Bandwidth Memory (HBM) for GPU servers), making throughput bottlenecked by memory bandwidth rather than compute. Speculative decoding addresses this by enabling parallel verification of multiple draft tokens, effectively amortizing the cost of each target-model call. However, existing speculative decoding methods are designed under the assumption that HBM is sufficiently large to hold both the target model and an auxiliary draft model simultaneously -- an assumption that breaks down on memory-constrained devices such as edge platforms with limited DRAM. We analyze the inference bottleneck in this memory-limited regime and propose CATS, a self-speculative decoding framework that conducts cascaded verification and correction based on the memory budget and parameter offloading patterns on memory-limited devices. This design maximizes token acceptance rate and end-to-end speedup while keeping the peak memory footprint on the device equal to that of the target model alone. We evaluate CATS on different models across five benchmarks on real edge devices. CATS can achieve a wall-clock speedup of up to 5.08x with no degradation in generation quality, outperforming the SOTA method by up to 1.45x under edge memory constraints.

Yuning Han, Yangchenchen Jin, Dylan Zhao +1

University of Florida Gainesville, FL 32611

On-Device Language Model Inference Memory-Efficient Inference Speculative Decoding LLM Inference Acceleration

May 11, 2026cs.LG

ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs

Large language models (LLMs) are costly to deploy due to their large memory footprint and high inference cost. Weight-activation quantization can reduce these costs, but low-bit activation quantization remains difficult because activation outliers induce large quantization error. Recent rotation-based methods address this by applying orthogonal transformations that redistribute activation magnitude across dimensions, but existing approaches either require expensive end-to-end rotation training or rely on stored activation corpora, introducing significant compute or storage overhead. We propose a lightweight post-training rotation calibration method for LLM activation quantization. Our method learns orthogonal rotations that align normalized activations with the corners of an inscribed hypercube, encouraging activation energy to be distributed more evenly across dimensions. This objective admits an efficient closed-form update via the orthogonal Procrustes problem, avoiding gradient-based optimization over the orthogonal group. We further introduce an online calibration procedure that updates rotations as calibration samples are processed, eliminating the need to store activations on disk and allowing rotations to adapt to quantized activation distributions during calibration. Experiments on Llama-2 and Llama-3 models from 3B to 70B parameters show that our method achieves competitive or improved performance across perplexity benchmarks and common sense reasoning tasks while avoiding both costly end-to-end training and large offline activation storage.

Chayne Thrash, Ali Abbasi, Soheil Kolouri

Department of Computer Science Vanderbilt University

Rotation-Based Quantization LLM Inference Acceleration Language Model Calibration Activation Quantization Post-Training Quantization

May 11, 2026cs.LG

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding

Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model proposes tokens which the target model then verifies in a single forward pass. Although the drafter network is small in modern architectures, its LM-head still performs projection to a large vocabulary, becoming one of the major computational bottlenecks. In prior work this issue has been predominantly addressed via static or dynamic vocabulary truncation. Yet mitigating the bottleneck, these methods bring in extra complexity, such as special vocabulary curation, sophisticated inference-time logic or modifications of the training setup. In this paper, we propose SlimSpec, a low-rank parameterization of the drafter's LM-head that compresses the inner representation rather than the output, preserving full vocabulary support. We evaluate our method with EAGLE-3 drafter across three target models and diverse benchmarks in both latency- and throughput-bound inference regimes. SlimSpec achieves

4\text{-}5\times

acceleration over the standard LM-head architecture while maintaining a competitive acceptance length, surpassing existing methods by up to

8\text{-}9\%

of the end-to-end speedup. Our method requires minimal adjustments of training and inference pipelines. Combined with the aforementioned speedup improvements, it makes SlimSpec a strong alternative across wide variety of draft LM-head architectures.

Anton Plaksin, Sergei Krutikov, Sergei Skvortsov +1

Nebius, Amsterdam, Netherlands.

LLM Compression Speculative Decoding LLM Inference Acceleration

May 11, 2026cs.LG

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration

Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving complex mathematical and programming tasks. However, its efficiency is constrained by the reward dependency barrier -- a synchronization bottleneck caused by sequential reward-guided exploration that limits search parallelism and introduces substantial latency. Prior system optimizations, mainly designed for linear Chain-of-Thought (CoT) reasoning, cannot address these challenges, leaving the efficiency of ToT underexplored. To enhance ToT reasoning efficiency, we observe that the reasoning paths can be explored speculatively to break the reward synchronization barrier. Therefore, in this paper, we propose SPEX and introduce three key techniques: (i) intra-query speculative path selection to predict and expand high-potential branches of ToT, (ii) inter-query budget allocation to balance speculative resource allocation across queries dynamically, and (iii) adaptive early termination to prune deep and redundant branches for a skewed search tree. We implement SPEX on top of the SGLang framework and evaluate it across diverse ToT algorithms and LLMs. Extensive experiments show that SPEX achieves

1.2 \sim 3 \times

speedup for different ToT reasoning algorithms. Moreover, SPEX synergizes with token-level speculative decoding, achieving cumulative speedups of up to

4.1\times

. Ablation studies further confirm the contributions of each technique. Overall, SPEX represents a significant step toward efficient and scalable ToT reasoning, unlocking the parallelism required for high-performance inference-time scaling for LLMs.

Shuzhang Zhong, Haochen Huang, Shengxuan Qiu +3

Institute for Artificial Intelligence, Peking University · School of Integrated Circuits, Peking University · 3ByteDance Seed

Inference-Time Search Tree of Thoughts LLM Inference Acceleration LLM Reasoning

May 11, 2026cs.NI

GELATO: Generative Entropy- and Lyapunov-based Adaptive Token Offloading for Device-Edge Speculative LLM Inference

The recent growth of on-device Large Language Model (LLM) inference has driven significant interest in device-edge collaborative LLM inference. As a promising architecture, Speculative Decoding (SD) is increasingly adopted where a lightweight draft model rapidly generates candidate tokens to be verified by a powerful target model. However, a fundamental challenge lies in achieving per-token resource scheduling to effectively adapt SD paradigm to resource-constrained edge environment. This paper proposes a Generative Entropy- and Lyapunov-based Adaptive Token Offloading framework, named GELATO, to maximize decoding throughput under energy constraints in a device-edge collaborative SD system. Specifically, an outer drift-plus-penalty loop makes online decisions to establish a reference drafting budget, managing long-term energy-throughput trade-off. Further, a nested entropy-driven generation mechanism executes early exiting to adapt to per-token dynamic generative uncertainty. Theoretical analysis establishes a rigorous performance bound on long-term throughput for GELATO. Extensive evaluations demonstrate that GELATO achieves a globally optimal tradeoff, outperforming state-of-the-art distributed SD architectures by 64.98% in token throughput and reducing energy consumption by 47.47% under resource-constrained environments, while preserving LLM decoding quality.

Zengzipeng Tang, Yuxuan Sun, Wei Chen +2

School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China

On-Device Language Model Inference Edge Computing Speculative Decoding LLM Inference Acceleration

May 11, 2026cs.LG

Attention Drift: What Autoregressive Speculative Decoding Models Learn

Speculative decoding accelerates LLM inference by drafting future tokens with a small model, but drafter models degrade sharply under template perturbation and long-context inputs. We identify a previously-unreported phenomenon we call \textbf{attention drift}: as the drafter generates successive tokens within a speculation chain, attention progressively moves from the prompt onto its own recently-generated tokens. We observe this across both \emph{EAGLE3} drafters and \emph{MTP heads}, suggesting drift is a property of drafter designs. We trace this to the un-normalized residual path between chain steps: the drafter's hidden state magnitude grows monotonically with chain depth, which exhibits dynamics consistent with additional pre-norm transformer layers stacked on the target rather than as a standalone autoregressive predictor. In order to limit the growth, we propose two architectural changes: Post-norm on the drafter hidden states and per-hidden-state RMSNorm after capturing target hidden states. Our interventions improve acceptance length over the current leading model, pre-norm EAGLE3, by up to

2\times

under template perturbation,

1.18\times

on long-context tasks, and

1.10\times

on seven standard benchmarks spanning multi-turn chat, math, and coding. Our changes also allow shorter train-time-test depths to generalize over longer drafting sequences.

Doğaç Eldenk, Payal Mohapatra, Yigitcan Comlek +3

Northwestern University · GE Aerospace · fal +1

Long-Context Language Model Inference Speculative Decoding Transformer Attention LLM Inference Acceleration Layer Normalization

May 11, 2026cs.CL

Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference

Data-intensive applications, ranging from large-scale retrieval systems to advanced data pipelines, are increasingly bottlenecked by the processing of highly redundant text corpora. We present Merlin, a local-first, agnostic, high-throughput deduplication and context optimization engine designed to mitigate these inefficiencies. Utilizing a highly optimized, SIMD-friendly open-addressing flat hash set combined with xxHash3-64, Merlin performs rapid, byte-exact deduplication of text passages and data chunks. While broadly applicable to any text-processing workflow, its impact is particularly pronounced in Large Language Model (LLM) ecosystems, such as Retrieval-Augmented Generation (RAG). Our empirical evaluations demonstrate an input reduction ranging from 13.9% in low-redundancy datasets to over 71% in high-redundancy pipelines, maintaining absolute data fidelity. Furthermore, we detail the system's integration architecture via the Model Context Protocol (MCP), enabling secure, zero-network-interception deployment across major IDEs and autonomous agents. This paper outlines the core algorithmic design, performance benchmarks, and the architectural principles required to process data at sustained speeds of up to 8.7 GB/s.

Sietse Schelpe

Corbenic AI, Inc.

LLM Inference Acceleration

May 10, 2026cs.LG

Entropy-informed Decoding: Adaptive Information-Driven Branching

Large language models (LLMs) achieve remarkable generative performance, yet their output quality is dependent on the decoding strategy. While sampling-based methods (e.g., top-k, nucleus) and search-and-select based methods (e.g., beam search, best-of-n, majority voting) can improve upon greedy decoding, both approaches suffer from limitations: sampling generally commits to a single path, while search often expends excessive computation regardless of task complexity. To address these, we introduce Entropy-informed decoding (EDEN), a plug-and-play, model-agnostic decoding framework that adaptively allocates computation based on the model's own uncertainty, approximating higher-width beam search with fewer expansions. At each generation step, EDEN estimates the entropy of the output token distribution and adjusts the branching factor monotonically with the entropy, expanding more candidates in high-entropy regions and following a greedier path in low-entropy regions, improving token efficiency. Experiments across complex tasks, including mathematical reasoning, code generation, and scientific questions, demonstrate that EDEN consistently improves output quality over existing decoding strategies, achieving better accuracy-expansion trade-offs than fixed-width beam search. By treating next-token selection as a noisy maximisation problem, we prove that branching factors monotone in entropy are guaranteed to find better (i.e. more probable) continuations than any fixed branching factor within the same total expansion budget, and derive explicit regret rates characterising the benefit of the adaptive allocation.

Benjamin Patrick Evans, Sumitra Ganesh, Leo Ardon

JP Morgan AI Research, London, UK · JP Morgan AI Research, New York, USA

Language Model Decoding LLM Inference Acceleration