LLM Inference Acceleration

Large language models (LLMs) can achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet they often generate unnecessarily long reasoning paths that incur high inference cost. Self-consistency-based approaches push accuracy higher still, but they require sampling and aggregating multiple reasoning trajectories, leading to substantial computational overhead. In this paper, we introduce a confidence-aware selective sampling framework that, at inference time, analyzes a single reasoning trajectory to adaptively determine whether to rely on that trajectory alone or trigger multi-path sampling. The framework uses trajectory-level numeric features and sentence-level linguistic features extracted from reasoning states to guide selective multi-path reasoning. We train it on MedQA and evaluate it in-domain on MedQA and under calibration-only transfer on MathQA, MedMCQA, and MMLU, without further fine-tuning. Experimental results show that the proposed framework maintains comparable performance to full and efficient multi-path reasoning baselines, with accuracy changes of $-0.41 \pm 0.58$ and $-0.31 \pm 0.58$ percentage points, respectively, while reducing token usage by $71.7 \pm 5.0$ and $36.6 \pm 9.1$. These findings demonstrate that reasoning trajectories contain rich signals for uncertainty estimation, enabling a simple, transferable mechanism to balance accuracy and efficiency in LLM reasoning.

Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts. A common strategy is to precompute key-value (KV) caches for individual documents and selectively recompute a small subset of tokens to restore global causal dependencies, but existing methods rely on heuristics or representation discrepancies without modeling whether selected tokens can effectively influence generation. We cast selective KV recomputation as an information flow problem and show that a simple attention-norm signal from the query reliably identifies tokens that are both semantically relevant and structurally positioned to propagate information, when computed under an inference-consistent RoPE geometry. We therefore reconstruct global positional assignments for retrieved chunks and introduce an information-flow-guided chunk reordering strategy. Experiments on Large Language Model and Vision-Language Model benchmarks demonstrate consistent gains over prior methods under comparable latency.

Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation. However, industrial recommender systems often benefit from restricting the output space to a constrained subset of items based on business logic (e.g. enforcing content freshness or product category), which standard autoregressive decoding cannot natively support. Moreover, existing constrained decoding methods that make use of prefix trees (Tries) incur severe latency penalties on hardware accelerators (TPUs/GPUs). In this work, we introduce STATIC (Sparse Transition Matrix-Accelerated Trie Index for Constrained Decoding), an efficient and scalable constrained decoding technique designed specifically for high-throughput LLM-based generative retrieval on TPUs/GPUs. By flattening the prefix tree into a static Compressed Sparse Row (CSR) matrix, we transform irregular tree traversals into fully vectorized sparse matrix operations, unlocking massive efficiency gains on hardware accelerators. We deploy STATIC on a large-scale industrial video recommendation platform serving billions of users. STATIC produces significant product metric impact with minimal latency overhead (0.033 ms per step and 0.25% of inference time), achieving a 948x speedup over a CPU trie implementation and a 47-1033x speedup over a hardware-accelerated binary-search baseline. Furthermore, the runtime overhead of STATIC remains extremely low across a wide range of practical configurations. To the best of our knowledge, STATIC enables the first production-scale deployment of strictly constrained generative retrieval. In addition, evaluation on academic benchmarks demonstrates that STATIC can considerably improve cold-start performance for generative retrieval. Our code is available at https://github.com/youtube/static-constraint-decoding.

Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to propose draft tokens that are subsequently verified by a larger target model. However, the performance of standard SD is often limited by the strictly sequential execution of these drafting and verification stages. To address this, this paper proposes MineDraft, a batch parallel speculative decoding (PSD) framework designed to effectively hide drafting latency by overlapping it with verification. Our theoretical analysis shows that PSD is substantially more efficient than standard SD. MineDraft realizes the PSD through a novel batch-parallel design that maintains two batches of requests, overlapping drafting for one batch with verification for the other. Our experimental results show significant improvements of \alg{} in both throughput (up to 75%) and end-to-end latency (up to 39%) over standard SD. Furthermore, we have implemented MineDraft as a plugin for vLLM, demonstrating its practicality for production-ready inference systems.

Simulating large-scale human mobility is fundamental to understanding population movement patterns and supporting real-world geospatial applications such as urban planning, epidemic response, and transportation analysis. Recent works treat large language models (LLMs) as human agents to simulate realistic mobility behaviors using structured reasoning, but their high computational cost limits scalability. To address this, we design a mobility-aware cache framework named MobCache that leverages reconstructible caches to enable efficient large-scale human mobility simulations. It consists of: (1) a reasoning component that encodes each reasoning step as a latent-space embedding and uses a latent-space evaluator to enable the reuse and recombination of reasoning steps; and (2) a decoding component that employs a lightweight decoder trained with mobility law-constrained distillation to translate latent-space reasoning chains into natural language, thereby improving simulation efficiency while maintaining fidelity. Experiments show that MobCache significantly improves efficiency across multiple dimensions while maintaining performance comparable to state-of-the-art LLM-based methods.

Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment. Two complementary approaches have emerged to address these issues: token-adaptive layer execution, which reduces floating-point operations (FLOPs) by selectively bypassing layers, and quantization, which lowers memory footprint by reducing weight precision. However, naively integrating these techniques leads to additional accuracy degradation due to reduced redundancy in token-adaptive models. We propose QTALE (Quantization-Robust Token-Adaptive Layer Execution for LLMs), a novel framework that enables seamless integration of token-adaptive execution with quantization while preserving accuracy. Conventional token-adaptive methods reduce redundancy in two ways: (1) by limiting the diversity of training paths explored during fine-tuning, and (2) by lowering the number of parameters actively involved in inference. To overcome these limitations, QTALE introduces two key components: (1) a training strategy that ensures diverse execution paths are actively explored during fine-tuning, and (2) a post-training mechanism that allows flexible adjustment of the execution ratio at inference to reintroduce redundancy when needed. Experimental results show that QTALE enables seamless integration of token-adaptive layer execution with quantization, while keeping the accuracy gap to quantization-only models below 0.5% on CommonsenseQA benchmarks. By combining tokenadaptive execution for FLOPs reduction and quantization for memory savings, QTALE provides an effective solution for efficient LLM deployment.

A core bottleneck in large language model (LLM) inference is the cost of attending over the ever-growing key-value (KV) cache. Although near-oracle top-k KV selection can preserve the quality of dense attention while sharply reducing computation and bandwidth, existing sparse methods generally rely on posterior heuristics, i.e., selectors conditioned on observed attention or proxy scores. Such conditioning introduces posterior bias: it tends to distort true token importance and miss salient tokens, thereby impairing long-range reasoning. To tackle this problem, we propose Pre-hoc Sparsity (PrHS), which selects KV entries before attention scoring and provides explicit accuracy control. Let the attention mass of discarded entries be delta (the dropped mass). Through a marginal-to-mutual-information analysis, we derive an upper bound on the mutual-information loss that depends only on the dropped mass. This relation explains failure modes of posterior heuristics and enables verifiable guarantees by controlling the dropped mass in advance. Within PrHS, we instantiate three orthogonal pre-hoc selectors along the axes of time, depth, and layer. Extensive experiments on LLaMA and Mistral families validate PrHS. Across GSM8K and CoQA, PrHS reduces retrieval overhead by over 90%, achieving 3x higher retrieval sparsity than HShare at matched or better accuracy. It incurs under 1% average degradation on LongBench, lowers attention FLOPs by about 15% versus prior sparse baselines, and yields a 9.9x speedup in attention-operator latency and 2.8x higher throughput on NVIDIA A100-80GB GPUs than the dense baseline.

Efficient long-context inference faces two coupled bottlenecks: KV-cache memory grows linearly with context length, while attention computation grows quadratically. Existing approaches typically address one at the expense of irreversible token eviction, full-cache retention, or full-history reconstruction, limiting their effectiveness for multi-turn interaction and long-form reasoning. Motivated by two empirical properties, Long-Range Inter-Token Similarity and Smooth Residual Distribution, we propose ResidualKV, which factorizes the KV cache into a sparse set of globally retrieved references and compact, quantized residual codes for the remaining tokens. This representation preserves token-specific information without permanent eviction and, when combined with sparse attention, reconstructs only the selected states on demand. Dynamic-stride scheduling further reduces reference growth from linear to approximately logarithmic at ultra-long contexts. Across Llama, Qwen, LLaVA-OV, and Qwen3-VL backbones, ResidualKV maintains near-full-cache performance using only 13%-16% KV storage and 30% attention computation on LongBench, and 8%-10% storage and 10% computation in matched-budget multimodal evaluation. It also accelerates decoding by up to $1.5\times$ with KV-cache quantization and $3.4\times$ without it. These results show that global cross-token redundancy supports accurate, memory-efficient, and computation-efficient long-context inference. The source code is available at https://github.com/CURRENTF/ResidualKV.

Mixture-of-Experts (MoE) architectures are evolving towards finer granularity to improve parameter efficiency. However, existing MoE designs face an inherent trade-off between the granularity of expert specialization and hardware execution efficiency. We propose OmniMoE, a system-algorithm co-designed framework that pushes expert granularity to its logical extreme. OmniMoE introduces vector-level Atomic Experts, enabling scalable routing and execution within a single MoE layer, while retaining a shared dense MLP branch for general-purpose processing. Although this atomic design maximizes capacity, it poses severe challenges for routing complexity and memory access. To address these, OmniMoE adopts a system-algorithm co-design: (i) a Cartesian Product Router that decomposes the massive index space to reduce routing complexity from O(N) to O(sqrt(N)); and (ii) Expert-Centric Scheduling that inverts the execution order to turn scattered, memory-bound lookups into efficient dense matrix operations. Validated on seven benchmarks, OmniMoE (with 1.7B active parameters) achieves 50.9% zero-shot accuracy across seven benchmarks, outperforming coarse-grained (e.g., DeepSeekMoE) and fine-grained (e.g., PEER) baselines. Crucially, OmniMoE reduces inference latency from 73ms to 6.7ms (a 10.9-fold speedup) compared to PEER, demonstrating that massive-scale fine-grained MoE can be fast and accurate. Our code is open-sourced at https://github.com/flash-algo/omni-moe.

Speculative decoding can substantially accelerate LLM inference, but realizing its benefits in practice is challenging due to evolving workloads. We present TIDE (Temporal Incremental Draft Engine), a serving-engine-native framework that integrates online draft adaptation directly into high-performance LLM inference systems. TIDE reuses target model's intermediate hidden states generated during inference as training signals for draft adaptation, thereby avoiding additional target model computation and serving-time overhead. It employs adaptive runtime control to activate speculation and draft model training only when beneficial. TIDE exploits heterogeneous clusters by mapping inference and training to appropriate GPU classes. Across diverse real-world workloads, TIDE achieves up to 1.66$\times$ throughput over no-speculation baselines while recovering performance on misaligned workloads where static draft models degrade throughput. TIDE also reduces training time by up to 3.02$\times$ and storage requirements by 24$\times$ compared to existing draft training approaches, and improves system throughput by up to 1.22$\times$ on heterogeneous GPU clusters.

Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The issue is exacerbated in Large Reasoning Models (LRMs), which generate lengthy chains of thought. While speculative decoding accelerates inference by drafting and verifying multiple tokens in parallel, existing methods operate at the token level and ignore semantic equivalence (i.e., different token sequences expressing the same meaning), leading to inefficient rejections. We propose SemanticSpec, a semantic-aware speculative decoding framework that verifies entire semantic sequences instead of tokens. SemanticSpec introduces a semantic probability estimation mechanism that probes the model's internal hidden states to assess the likelihood of generating sequences with specific meanings. Experiments on four benchmarks show that SemanticSpec achieves up to 2.7x speedup on DeepSeekR1-32B and 2.1x on QwQ-32B, consistently outperforming token-level and sequence-level baselines in both efficiency and effectiveness.

Matryoshka Quantization (MatQuant), Any-Precision-LLM (AP) and AnyBCQ (AB) are recent quantization approaches showing that a single integer-quantized model can be served across multiple precisions. In this paradigm, lower-precision models are extracted from a higher-precision model by simply reading fewer bits of the weights. This enables a single checkpoint to cover a wide range of memory and latency budgets, but makes both quantization and efficient execution substantially harder. Existing methods rely on expensive quantization-aware training (QAT) or gradient-based post-training quantization (PTQ) rather than fast one-shot PTQ, and offer limited system support: dedicated kernels are either missing or restricted to single- or small-batch decoding. We address these limitations with Post-Training Matryoshka Quantization (MatGPTQ), an end-to-end pipeline for nested-model quantization and inference. MatGPTQ casts Matryoshka quantization as multi-precision error compensation, producing a single "sliceable" parent model jointly optimized for multiple target precisions in one pass over a small calibration set. We further refine the MatQuant representation so that an $r$-bit model reads exactly $r$ bits, and introduce the first dedicated inference kernels for this format, supporting batch sizes beyond one and integrated into vLLM. Across standard LLMs and benchmarks, MatGPTQ outperforms MatQuant while remaining competitive with AP and AB at the smallest checkpoint size, and our kernels achieve end-to-end speedups of up to 3.5$\times$ over BF16 at the low-bit regime. Overall, MatGPTQ makes nested quantized models practical to serve from a single, compact checkpoint. Code is available at https://github.com/IST-DASLab/MatGPTQ.

Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexity of standard softmax attention. Existing methods perform token routing based on sliding-window partitions, resulting in position-based selection and fails to capture token-specific global importance. Meanwhile, linear attention further suffers from distribution shift caused by learnable feature maps that distort pretrained feature magnitudes. Motivated by these limitations, we propose STILL, an intra-layer hybrid linearization framework for efficiently linearizing LLMs. STILL introduces a Self-Saliency Score with strong local-global consistency, enabling accurate token selection using sliding-window computation, and retains salient tokens for sparse softmax attention while summarizing the remaining context via linear attention. To preserve pretrained representations, we design a Norm-Preserved Feature Map (NP-Map) that decouples feature direction from magnitude and reinjects pretrained norms. We further adopt a unified training-inference architecture with chunk-wise parallelization and delayed selection to improve hardware efficiency. Experiments show that STILL matches or surpasses the original pretrained model on commonsense and general reasoning tasks, and achieves up to a 86.2% relative improvement over prior linearized attention methods on long-context benchmarks. Code is available at this URL.

Large reasoning models (LRMs) typically solve reasoning-intensive tasks by generating long chain-of-thought (CoT) traces, leading to substantial inference overhead. We identify a reproducible inference-time phenomenon, termed Self-Compression: when multiple independent and answerable questions are presented within a single prompt, the model spontaneously produces shorter reasoning traces for each question. This phenomenon arises from multi-question contextual pressure during generation and consistently manifests across models and benchmarks. Building on this observation, we propose ConPress (Learning from Contextual Pressure), a lightweight self-supervised fine-tuning approach. ConPress constructs multi-question prompts to induce self-compression, samples the resulting model outputs, and parses and filters per-question traces to obtain concise yet correct reasoning trajectories. These trajectories are directly used for supervised fine-tuning, internalizing compressed reasoning behavior in single-question settings without external teachers, manual pruning, or reinforcement learning. With only 8k fine-tuning examples, ConPress reduces reasoning token usage by 59% on MATH500 and 33% on AIME25, while maintaining competitive accuracy.

Long chain-of-thought reasoning (Long CoT) is now fundamental to state-of-the-art LLMs, especially in mathematical reasoning. However, LLM generation is highly sequential, and long CoTs lead to a high latency. We propose to train Divide-and-Conquer CoT (DC-CoT) to reduce the latency. With DC-CoT, the model can act as a director that identifies distinct subtasks that can be performed in parallel in its reasoning process, and then spawns workers to execute the subtasks. Our goal is to achieve high accuracy, with a low longest path length, which is a theoretical measure of the latency needed for the response. We start with a long CoT base model (DeepScaleR-1.5B-Preview), and first use SFT with a small curated demonstration set to initialize its ability to spawn workers in a certain format. Because SFT degrades the accuracy significantly, we design a multi-stage RL algorithm, with various data filtering strategies, to recover the accuracy while decreasing the longest path length. Across several benchmarks including AIME 2024 and HMMT 2025, DC-CoT achieves similar accuracy as DeepScaleR-1.5B-Preview while decreasing longest path length by 35-40%. Our code, SFT dataset and models are publicly available at https://github.com/amahankali10/DC_CoT_RL_for_Low_Latency_CoT_with_Parallel_Reasoning.

The emergence of fine-grained numerical formats like NVFP4 presents new opportunities for efficient Large Language Model (LLM) inference. However, it is difficult to adapt existing Post-Training Quantization (PTQ) strategies to these formats: rotation-based methods compromise fine-grained block isolation; smoothing techniques struggle with significant 4-bit quantization errors; and mixed-precision approaches often conflict with hardware constraints on unified-precision computation. To address these challenges, we propose ARCQuant, a framework that boosts NVFP4 performance via Augmented Residual Channels. Distinct from methods that compromise block isolation or hardware uniformity, ARCQuant maintains a strictly unified NVFP4 format by augmenting the activation matrix with quantized residual channels. This design integrates the error compensation process directly into the matrix reduction dimension, enabling the use of standard, highly optimized GEMM kernels with minimal overhead. Theoretical analysis confirms that the worst-case error bound of our dual-stage NVFP4 quantization is comparable to that of standard 8-bit formats such as MXFP8. Extensive experiments on LLaMA and Qwen models demonstrate that ARCQuant achieves state-of-the-art accuracy, comparable to full-precision baselines in perplexity and downstream tasks. Furthermore, deployment on RTX 5090 and RTX PRO 6000 GPUs confirms practical benefits, achieving up to 3x speedup over FP16. Our code is available at https://github.com/actypedef/ARCQuant.

Judge Decoding accelerates LLM inference by relaxing the strict verification of Speculative Decoding, yet it typically relies on expensive and noisy supervision. In this work, we revisit this paradigm from first principles, revealing that the ``criticality'' scores learned via costly supervision are intrinsically encoded in the draft-target distributional divergence. We theoretically prove a structural correspondence between learned linear judges and Kullback-Leibler (KL) divergence, demonstrating they rely on the same underlying logit primitives. Guided by this, we propose a simple, training-free verification mechanism based on KL divergence. Extensive experiments across reasoning and coding benchmarks show that our method matches or outperforms complex trained judges (e.g., AutoJudge), offering superior robustness to domain shifts and eliminating the supervision bottleneck entirely. Code is available at https://github.com/sunshy-1/JuDi

Speculative decoding (SD) accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens and a stronger target model to verify them. However, standard SD is mainly designed for acceleration, and its output quality is typically constrained by the target model. In this work, we propose Entropy-Aware Speculative Decoding (EASD), a lightweight and training-free extension of SD that improves reasoning quality through token-level entropy-guided rejection. EASD detects cases where both draft and target models exhibit high uncertainty while strongly overlapping in their top predictions. In such uncertain-agreement cases, EASD rejects the aligned token and resamples from the target distribution, preventing low-confidence errors from propagating. Experiments on challenging reasoning benchmarks show that EASD consistently improves accuracy over standard SD and reward-guided variants while maintaining comparable inference efficiency. Notably, EASD can surpass the standalone performance of the target model, suggesting that speculative decoding can serve not only as an acceleration method but also as an effective mechanism for improving reasoning quality. The code is available at https://github.com/ECNU-Text-Computing/EASD.

Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG. We propose Kascade, a training-free sparse attention method that leverages known observations such as 1) post-softmax attention is intrinsically sparse, and 2) the identity of high-weight keys is stable across nearby layers. Kascade computes exact Top-k indices in a small set of anchor layers, then reuses those indices in intermediate reuse layers. The anchor layers are selected algorithmically, via a dynamic-programming objective that maximizes cross-layer similarity over a development set, allowing easy deployment across models. The method incorporates efficient implementation constraints (e.g. tile-level operations), across both prefill and decode attention. The Top-k selection and reuse in Kascade is head-aware and we show in our experiments that this is critical for high accuracy. Kascade achieves up to 4.1x speedup in decode attention and 2.2x speedup in prefill attention over FlashAttention-3 baseline on H100 GPUs while closely matching dense attention accuracy on long-context benchmarks such as LongBench and AIME-24.

Recommendation system delivers substantial economic benefits by providing personalized predictions. Generative recommendation (GR) integrates LLMs to enhance the understanding of long user-item sequences. Despite employing attention-based architectures, GR's workload differs markedly from that of LLM serving. GR typically processes long prompt while producing short, fixed-length outputs, yet the computational cost of each decode phase is especially high due to the large beam width. Furthermore, since the beam search involves a vast item space, the sorting overhead becomes particularly time-consuming. We propose xGR, a GR-oriented serving system that meets strict low-latency requirements under high-concurrency scenarios. First, xGR unifies the processing of prefill and decode phases through staged computation and separated KV cache. Second, xGR enables early sorting termination and mask-based item filtering with data structure reuse. Third, xGR reconstructs the overall pipeline to exploit multi-level overlap and multi-stream parallelism. The experiments on real-world datasets demonstrate that xGR achieves at least 2.89x throughput compared to the state-of-the-art baseline under strict latency constraints.

Modern large language models increasingly require long contexts for reasoning and multi-document tasks, but attention's quadratic complexity creates a severe computational bottleneck. We present Block Sparse Flash Attention (BSFA), a drop-in replacement that accelerates long-context inference while preserving model quality. Unlike methods that predict importance before computing scores, BSFA computes exact query-key similarities to select the top-k most important value blocks for each query. By comparing per-block maximum scores against calibrated thresholds, we skip approximately 50% of the computation and memory transfers for pruned blocks. Our training-free approach requires only a one-time threshold calibration on a small dataset to learn the per-layer and per-head attention score distributions. We provide a CUDA kernel implementation that can be used as a drop-in replacement for FlashAttention. On Llama-3.1-8B, BSFA achieves up to 1.13x end-to-end speedup on LongBench with only a 1.1% accuracy drop, and up to 1.24x on Needle-in-a-Haystack retrieval at a 1% accuracy drop. The attention kernel itself accelerates by up to 1.38x. We compare BSFA against five recent sparse attention baselines (SpargeAttention, MInference, FlexPrefill, XAttention, and BLASST), and verify the method on Qwen2.5-7B and on A6000 and H100 GPUs. The implementation is available at https://github.com/Danielohayon/Block-Sparse-Flash-Attention.

Businesses increasingly rely on large language models (LLMs) to automate simple repetitive tasks instead of developing custom machine learning models. LLMs require few, if any, training examples and can be utilized by users without expertise in model development. However, this comes at the cost of substantially higher resource and energy consumption compared to smaller models, which often achieve similar predictive performance for simple tasks. In this paper, we present our vision for just-in-time model replacement (JITR), where, upon identifying a recurring task in calls to an LLM, the model is replaced transparently with a cheaper alternative that performs well for this specific task. JITR retains the ease of use and low development effort of LLMs, while saving significant cost and energy. We discuss the main challenges in realizing our vision regarding the identification of recurring tasks and the creation of a custom model. Specifically, we argue that model search and transfer learning will play a crucial role in JITR to efficiently identify and fine-tune models for a recurring task. Using our JITR prototype Poodle, we reduce inference time by up to 7.5x compared to a self- hosted LLM and save more than $2,200 per 1M requests compared to a flagship hosted LLM, while achieving accuracy competitive with the LLM baseline.

Many self-attention sublayers in large language models (LLMs) can be removed with little to no loss. We attribute this to the Attention Suppression Hypothesis: during pre-training, some deep attention layers learn to mute their own contribution, leaving the residual stream and the MLP to carry the representation. We propose Gate-Norm, a one-shot, weight-only criterion that ranks attention sublayers by query-key coupling and removes the least coupled ones, requiring no calibration data, no forward passes, no fine-tuning, and no specialized kernels. On 40-layer, 13B-parameter LLaMA models, Gate-Norm prunes the model in under a second. Pruning 8-16 attention sublayers yields up to $1.30\times$ higher inference throughput while keeping average zero-shot accuracy within 1.5 percentage points of the unpruned baseline across BoolQ, RTE, HellaSwag, WinoGrande, ARC-Easy/Challenge, and OpenBookQA. Across these settings, Gate-Norm matches data-driven pruning methods in accuracy while being $\sim 1000\times$ faster to score layers, enabling practical, data-free compression of LLMs.

Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but their inherently sequential decoding incurs substantial latency, motivating parallelization of the generation process. However, existing parallel reasoning approaches suffer from performance degradation compared to their sequential counterparts, and often rely on specialized inference engines. We introduce ThreadWeaver, a framework for adaptive parallel reasoning that matches the accuracy of comparably sized sequential reasoning models while significantly reducing inference latency via three key innovations: 1) a two-stage parallel trajectory generator that produces high-quality parallel chain-of-thought data for supervised fine-tuning; 2) a trie-based rollout design that enables parallel reasoning on any off-the-shelf autoregressive inference engine; and 3) a parallelization-aware reinforcement learning framework that trains the model to balance reasoning accuracy with effective parallelization. Across six challenging math reasoning benchmarks, ThreadWeaver trained on top of Qwen3-8B achieves performance on par with cutting-edge sequential reasoning models (79.9% on AIME24 and 71.9% on average) while delivering up to 1.53x speedup in token latency, establishing a new Pareto frontier between accuracy and efficiency.

High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Learning (ML) models, including Large Language Models (LLMs), by leveraging the large memory bandwidth available at PIM cores. However, Host processor needs consecutive elements distributed across DRAM banks, while PIM cores need consecutive elements within their local banks. This necessitates data rearrangements in ML kernel execution that pose significant performance and programmability challenges, further exacerbated by the need to support diverse PIM devices. Current compilation approaches lack systematic optimization for diverse ML kernels and multiple PIM devices, and may largely ignore data rearrangement costs during the compute code optimization step. We show that data rearrangements and compute code optimization are interdependent, and need to be jointly optimized during the tuning process. Therefore, we design DCC, the first data-centric ML compiler for PIM systems that jointly co-optimizes data rearrangements and compute code in a unified tuning process. DCC integrates a multi-layer PIM abstraction to support multiple PIM backends. DCC enables effective co-optimization of data partitioning strategies with compute loop partitioning schemes. DCC applies PIM-specific code optimizations, and leverages a fast and accurate performance prediction model to select the bestperforming code schedule for a given kernel on a target PIM architecture. Our evaluations in various individual ML kernels show that DCC achieves up to 7.68x speedup (2.21x average) on HBM-PIM, and up to 13.17x speedup (3.92x average) on AttAcc PIM, over GPU-only execution. In end-to-end LLM inference, DCC on AttAcc accelerates GPT-3 and LLaMA-2 by 4.52x average (up to 7.71x in LLaMA-2) over GPU. DCC is open-sourced at https://github.com/SPIN-Research-Group/DCC.

Long Chain-of-Thought (CoT) traces can improve reasoning accuracy, but repeatedly generating them is costly for smaller or latency-constrained language models. This paper studies a practical alternative: produce a rich rationale once with a capable \emph{thinking} model, compress it, and reuse the compressed trace as context for a cheaper \emph{answering} model. We introduce CoT-X, an adaptive framework for cross-model CoT transfer. CoT-X segments reasoning traces into semantic units, scores their diagnostic and logical importance, selects budget-feasible evidence paths, and reconstructs a coherent compressed rationale for the answering model. On $7,501$ Japanese medical licensing questions spanning $10$ specialties, CoT-X improves accuracy over direct truncation by up to $40.5\%$ under the same token budget, with the largest gains at $64$--$256$ tokens. Across $64$ thinking--answering pairs from eight DeepSeek-R1 and Qwen3 models (1.5B--32B parameters), reasoning transfer is most reliable within a model family, yet remains effective across families once compression normalizes the trace. A Gaussian Process Bayesian optimization layer finds near-optimal model--budget configurations with $15$ evaluations rather than an exhaustive search over all $64$ pairs, reducing evaluation cost by $84\%$. These results show that reasoning quality, token budget, and model compatibility can be optimized jointly, making CoT-style reasoning more practical under realistic deployment constraints.

Processing long documents with large language models (LLMs) is expensive: a single query over a 100K-token document can cost from tens of cents to over a dollar in API fees, depending on the model, and memory grows linearly with context length. We introduce BudgetMem, a training-free architecture that keeps only high-salience content under an explicit memory budget. Unlike token-level neural compressors such as LLMLingua, BudgetMem makes chunk-level keep-or-discard decisions from interpretable features: entity density, TF-IDF importance, position, numerical density, discourse markers, and question presence. Across four benchmarks, BudgetMem matches the uncompressed baseline on template-generated structured documents (F1 = 0.859 vs. 0.855) while discarding 70% of chunks. As a pre-retrieval filter on the same documents it outperforms LLMLingua-2 by a wide margin (0.859 vs. 0.554), because token-level compression destroys the phrasal structure that retrieval depends on; the advantage holds across model scale and family (Llama-3.2-3B, Qwen2.5-7B), under dense retrieval (0.918 vs. 0.530), and in LLMLingua-2's intended direct-feed mode (0.797 vs. 0.720). On real NLP research papers (Qasper), BudgetMem is competitive but not free, trailing the full baseline by 7.4% and LLMLingua-2 by 5.5% relative F1 at a 72% storage reduction. Removing discourse markers or numerical density hurts most, although TF-IDF alone scores as well on template documents. The pipeline needs no trained models or GPU for compression and runs on a $10/month Colab instance.

Decoding throughput improvements from larger inference batches are limited by GPU memory, which is largely consumed by the key-value (KV) cache. Prior training-free KV cache offloading alleviates this by keeping redundant context on the CPU and fetching only a sparse subset for attention, but it often degrades long-generation quality due to training-inference mismatch on sparse patterns. Meanwhile, trainable sparse attention is incompatible with efficient offloading, as unconstrained KV accesses may force large CPU-to-GPU transfers and erase throughput gains. To this end, we propose NOSA, a trainable sparse attention mechanism natively designed for KV cache offloading. NOSA explicitly constrains the volume of CPU-GPU KV transfers, thereby achieving low communication overhead and high decoding throughput. We further build NOSI, a KV cache offloading inference system that fully unlocks NOSA's efficiency. Empirical results on 1,3,8B LLMs demonstrate that NOSA outperforms KV cache offloading baselines on general, long-input, and long-generation tasks, while boosting decoding throughput by up to 5.04x, 1.92x, and 1.83x over FullAttn, InfLLMv2, and ShadowKV, respectively. We release our code at https://github.com/thunlp/NOSA.

Attention is a core operation in large language models (LLMs). We present BD Attention (BDA), a lossless algorithmic reformulation of attention. BDA is enabled by a simple matrix identity from Basis Decomposition (BD), which restructures multi-head projections into a compact form while preserving exact outputs. Unlike I/O-aware system optimizations such as FlashAttention, BDA provides a mathematically guaranteed acceleration that is architecture-agnostic. On DeepSeek-V2-Lite (16B, FP16), BDA requires only 4s of offline preparation with no retraining required and, on modern GPUs, achieves 34% faster key/value projections and 25% smaller weights, while increasing perplexity (PPL) by just 0.02% (FP16) or 0.0004% (FP32), a negligible effect on model performance. These results position BDA as a theoretically exact method for lossless attention acceleration that is complementary to existing engineering-level optimizations. Our code is available at https://github.com/abcbdf/basis-decomposition-official.

Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in line with task difficulty. On one hand, short reasoning (underthinking) leads to errors on harder problems that require extended reasoning steps; but, excessively long reasoning (overthinking) can be token-inefficient by generating unnecessary steps even after reaching a correct intermediate solution. We refer to this as under-adaptivity, where the model fails to modulate its response length appropriately given problems of varying difficulty. To address under-adaptivity and strike a balance between under- and overthinking, we propose TRAAC (Think Right with Adaptive, Attentive Compression), an online post-training RL method that leverages the model's self-attention to identify key steps and prune redundant ones. TRAAC also estimates difficulty and incorporates it into training rewards, thereby learning to allocate a reasoning budget commensurate with example difficulty. Across a variety of tasks (AIME, AMC, GPQA-D, BBEH), TRAAC (Qwen3-4B) achieves an average absolute accuracy gain of 8.4% with a relative reduction in reasoning length of 36.8% compared to the base model, and a 7.9% accuracy gain paired with a 29.4% length drop compared to the best RL baseline. TRAAC generalizes well, with accuracy and efficiency gains on out-of-distribution non-math datasets like GPQA-D, BBEH, and OptimalThinkingBench. Our analysis shows that TRAAC learns to adjust its thinking budget based on difficulty and that a combination of task-difficulty calibration and attention-based compression yields gains across diverse tasks.