生成模型与LLM推理优化

World models are transitioning from passive visual generators to foundational, operational infrastructure for Physical AI: they must natively acquire world knowledge from heterogeneous experience, maintain persistent states over long horizons, and execute efficiently within real deployment constraints. We introduce Kairos, a native world model stack designed around these requirements. (1) Kairos learns the world by pioneering a Native Pre-training Paradigm governed by a Cross-Embodiment Data Curriculum, which organizes open-world videos, human behavioral data, and robot interactions into a progressive developmental pathway. (2) Kairos maintains the world by unified world understanding, generation, and prediction within a Native Unified Architecture equipped with Hybrid Linear Temporal Attention, where sliding-window attention captures local dynamics, dilated sliding windows capture mid-range dependencies, and gated linear attention maintains persistent global memory. We establish formal theoretical bounds demonstrating that this temporal factorization strictly limits error accumulation, mathematically guaranteeing state propagation across extended horizons. (3) Kairos runs the world by incorporating a Deployment-Aware System Co-Design to support low-latency rollout generation on server and consumer-grade hardware for real-world observation-action-feedback loops. Experiments on embodied world-model, long-horizon, and action-policy benchmarks show that Kairos achieves top level performance while offering a strong efficiency-capability trade-off. Together, these results position Kairos as a cohesive operational foundation for future self-evolving physical intelligence.

Query-key (QK) normalization stabilizes attention by controlling the scale of queries and keys before the dot product, but is not immediately compatible with Multi-head Latent Attention (MLA). MLA achieves efficient decoding by caching low-dimensional latent states instead of full keys, whereas post-projection QK RMSNorm appears to require the fully projected key for every cached token. We show this apparent incompatibility is an implementation artifact, not an architectural constraint. RMSNorm decomposes into a static affine weight and a dynamic scalar RMS statistic. The static key-side weight can be absorbed into the MLA query-side projection; the dynamic key statistic reduces to one inverse-RMS scalar per token and KV group. The resulting formulation is exactly equivalent to explicit post-projection QK RMSNorm in exact arithmetic and preserves MLA's latent decode path. In our 400M runs trained for up to 100B tokens, QK-Normed MLA achieves lower training loss and better downstream accuracy than QK clipping, while H800 decode benchmarks show less than 2% latency overhead up to 256k context. These results make QK normalization a practical stabilization option for MLA models without requiring full-key caching.

Streaming data systems increasingly underpin Machine Learning workflows that maintain large numbers of continuously updated aggregations. In production settings, each incoming event typically triggers read-modify-write operations to persistent storage, making high-frequency state updates a dominant source of latency, contention, and operational cost. In this work, we decouple inference from state persistence in streaming Machine Learning pipelines via probabilistic thinning: every event is scored, but durable state updates are selectively triggered by informative events. Unlike approaches that shed input or state, we show that persistence-path control is achievable without a high-frequency in-memory control plane or cross-worker coordination, relying exclusively on approximate statistics retrieved from disk-backed key-value stores. We model the resulting stochastic processes, derive bounds on filtering rates, and prove that common time-based aggregations remain unbiased under variance-aware formulations, preventing systemic error accumulation. We evaluate the approach in a controlled setting that isolates per-event costs, demonstrating substantial reductions in storage Input/Output and serialization overhead. Across experiments, up to 90% of events are excluded from the persistence path while preserving and in some cases improving downstream utility.

As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their unconstrained sequence mutations alter layouts, introducing prefix mismatches and cache invalidation. This reveals a critical trade-off between text sparsity and prompt cache continuity. To address this, we present TokenPilot, a dual-granularity context management framework. Globally, Ingestion-Aware Compaction acts as a framework harness to stabilize prompt prefixes and eliminate open-world environmental noise at the ingestion gate. Locally, Lifecycle-Aware Eviction monitors the ongoing residual utility of context segments, enforcing a conservative batch-turn schedule to offload content segments only when task relevance expires. Experiments on PinchBench and Claw-Eval under both isolated and continuous modes demonstrate that TokenPilot reduces costs by 61% and 56% in isolated mode, and 61% and 87% in continuous mode, while maintaining competitive performance compared to prior systems. TokenPilot has been integrated into LightMem2 at https://github.com/zjunlp/LightMem2.

Post-training quantization (PTQ) enables efficient deployment of deep networks using a small set of data. Its application to visual autoregressive models (VAR), however, remains relatively unexplored. We identify two key challenges for applying PTQ to VAR: (i) large reconstruction errors in attention-value products, especially at coarse scales where high attention scores occur more frequently; and (ii) a discrepancy between the sampling frequencies of codebook entries and their predicted probabilities due to limited calibration data. To address these challenges, we propose a PTQ framework tailored for VAR. First, we introduce a shift-and-sum quantization method that reduces reconstruction errors by aggregating quantized results from symmetrically shifted duplicates of value tokens. Second, we present a resampling strategy for calibration data that aligns sampling frequencies of codebook entries with their predicted probabilities. Experiments on class-conditional image generation, inpainting, outpainting, and class-conditional editing show consistent improvements across VAR architectures, establishing a new state of the art in PTQ for VAR.

To guarantee service quality in transformer based large language model (LLM) serving, it is essential to meet the latency constraints of both the prefill phase (measured by Time-to-First-Token, TTFT) and the decode phase (measured by Time-per-Output-Token, TPOT). Non-disaggregated serving places prefill and decode on the same worker, while disaggregated serving places the prefill and decode on isolated workers. However, no single architecture excels in both TTFT and TPOT metrics. After conducting a root cause analysis, we concluded that indisaggregated LLM serving, prefill execution has minimal interference with decode execution but result in high queuing times. In contrast,non-disaggregated LLM serving effectively reduces queuing times but introduces significant interference between prefills and decodes. In order to leverage the best aspects of both non-disaggregated anddisaggregated LLM serving, we have designed and implemented Tropical.Tropical introduces an sevice-level objectives (SLO)-aware multiplexing strategy that balances the queuing time and the interference, enabling the LLM serving to achieve high TTFT and TPOT SLOs simultaneously. Our evaluation of real-world datasets reveals that Tropical outperforms both state-of-the-art non-disaggregated and disaggregated LLM serving systems, achieving up to 2.09 more requests within a 90% SLO attainment. Specially, compared to the disaggregated LLM serving system, Tropicalimproves P90 TTFT performance by 9 with only an 15% reduction in P90 TPOT. Against the non-disaggregated LLM serving systems, Tropicaldelivers a 2.8 performance improvement in P90 TPOT while maintaining the same P90 TTFT.

Modern CPUs increasingly integrate matrix extensions, such as Arm Scalable Matrix Extension (SME), that provide high-throughput matrix execution within the CPU. For LLM inference, however, these units are not a universal replacement for conventional CPU cores: prefill, decode, attention, and KV-cache operations expose different arithmetic intensities, vector behavior, and layout requirements, while SME units and CPU cores still compete for shared memory bandwidth. This paper studies this mismatch through a roofline-based characterization of SME-enabled CPUs and uses the resulting model to guide operator-level execution choices. We present SMEPilot, an LLM inference engine that selects CPU-only, SME-only, or cooperative SME+CPU execution for each operator shape. SMEPilot partitions matrix work across SME and CPU cores at tile granularity, overlaps SME-suitable matrix stages with CPU-suitable vector stages in attention, and maintains layout state so packed tensor representations are reused rather than repeatedly rebuilt on critical paths. Across Llama-3.2-3B, Qwen3-4B, and Qwen3-30BA3B on phone, PC, and server platforms, SMEPilot improves end-to-end inference performance by up to 3.94$\times$.

Computation integrity of remote large language model (LLM) serving can be questionable. For conventional deep neural networks (DNNs), the existing TEE-shielded DNN partitioning (TSDP) approach uses Trusted Execution Environment (TEE) to compute non-linear components and verify the integrity of linear components offloaded to an untrusted GPU. However, directly applying TSDP to Transformer-based LLMs incurs significant TEE computation and TEE-GPU communication overhead. This paper presents Communication-efficient TEE-GPU Attention (\textsc{VeriAttn}) for accelerating verifiable LLM inference. \textsc{VeriAttn} offloads both linear and non-linear computations of attention to the GPU, while TEE performs verification. Moreover, for prefill, \textsc{VeriAttn} uses a two-level pipeline to overlap data movement, TEE pre-/post-processing, and GPU computation. For decoding, when the key-value cache exceeds available GPU memory, \textsc{VeriAttn} partitions attention across TEE and GPU to reduce repeated key-value transfers. Evaluation on an Intel TDX platform shows that \textsc{VeriAttn} achieves 2.60-3.38$\times$ and 3.86-5.42$\times$ acceleration over TSDP for 6k-token prompts and 10k-token outputs during prefill and decoding, respectively.

Coding agents are a fast-growing LLM application, executing as long-running closed-loop sessions in which LLM generations alternate with external tool calls. Yet, unlike chat workloads, their serving behavior has not been studied extensively. We address this gap by collecting a dataset of real-world coding assistant traces. Our analysis shows that coding agent sessions repeatedly reuse large prefixes and create sustained KVCache pressure that conventional LLM serving policies handle poorly. Based on our analysis, we present CacheWise, a KVCache management layer that improves KVCache reuse for coding agent workloads. CacheWise combines prefix-aware scheduling with reuse-aware eviction guided by lightweight predictions from tool call metadata. Implemented in vLLM and evaluated on the collected traces, CacheWise reduces KVCache evictions by up to 2-2.6x and improves total agent session completion time by up to 3.5x.

Sparse attention accelerates Diffusion Transformers (DiTs) for video generation by computing only the important tokens while skipping the rest. The token selection strategy is key to balancing sparsity and accuracy. We formulate the token filtering process as a dual-goal optimization problem: maximizing sparsity and minimizing accuracy degradation. Existing algorithms cannot fulfill both objectives simultaneously. For example, Top-p only considers the accuracy constraint, while Top-k maintains a fixed computational budget but loosens the accuracy constraint. This paper demonstrates that maintaining a fixed recall rate is sufficient for ensuring accuracy, whereas a fixed threshold is suboptimal for reducing computational cost. Therefore, we propose a dynamic thresholding scheme to improve sparsity while maintaining the same level of accuracy. Furthermore, our algorithm is deeply integrated with Flash Attention (FA), eliminating the need for any additional masking computation overhead. Experimental results on Wan 2.2 validate that, compared to the BLASST algorithm which is also integrated with FA, our dynamic thresholding strategy enhances sparsity from 61.42% to 82% with a VBench metric drop of less than 5%. This results in an approximate 15% in attention computation and a $1.61\times$ increase in computational efficiency, which is 1.18x higher than that of BLASST.

Multi-turn conversation is a fundamental scenario in LLM applications, widely used in chatbots and AI agents. As the conversation evolves, historical tokens accumulate continuously. Existing systems cache their key-value (KV) pairs to avoid redundant computation. However, limited GPU memory (HBM) capacity often forces these KV caches to be offloaded to CPU memory or SSD, making KV cache reloads increasingly costly in terms of latency as the context grows. Meanwhile, the constrained HBM capacity also limits the maximum inference length, thereby restricting the number of turns that can be supported in a conversation. To address these two challenges, we propose SwiftCache, a collaborative inference system that enables heterogeneous models to share underutilized GPU memory and NVLink bandwidth within a server. Specifically, models with low KV cache demand donate idle GPU memory to store the prefix cache of high-demand models, allowing cross-model KV cache sharing over NVLink and avoiding slow PCIe transfers. SwiftCache further reduces memory pressure by keeping only the KV cache of the currently active layer in local GPU memory, thereby enabling longer-context inference. Our experiments on real-world workloads show that SwiftCache reduces P99 time-to-first-token (TTFT) by up to 69% and extends maximum context length by up to 3.98x compared to vLLM and SGLang, with minimal interference to co-located models.

Vision language models are serving as general-purpose interfaces for complex multimodal tasks. However, deployment still faces three gaps: VLMs typically incur high latency and cost when processing dense video frames and long prompts, the agent scaffold remains static after deployment, and standard video-QA benchmarks do not test whether agents can use visual evidence inside tool-using workspaces. We present VisualClaw, a self-evolving multimodal agent built around two principles. First, hybrid encoding reduces deployment cost by filtering less informative streaming frames with a cascaded gate and compressing the text skill bank through hot/cold top-k injection. Second, skill evolution lets the agent learn from failures: retrieved memories condition an evolver as direct concatenated context or as guided evidence, producing skill-bank updates that help future questions. Across 4 video-QA benchmarks with 2 VLMs, VisualClaw cuts per-question API cost by an average -98% versus full-frame upload and by -25.9% over the offline uniform 8 frame baseline, while boosting accuracy in most settings, e.g., an average +3.85% and a peak +15.80% on EgoSchema with Gemini 3 Flash. To address the gap, we curate VisualClawArena, a 200-scenario multimodal agentic benchmark built through a strict five-stage pipeline; models must use video evidence, documents, dynamic updates, and executable checks inside a workspace. On VisualClawArena, the same framework with computer-use agent backends improves macro accuracy by +2.9% for Codex (GPT-5.5) and +3.2% for Claude Code (Sonnet 4.6) over no-evolution baselines, with a -9.5% cost reduction compared to the uniform-sampled baseline. These properties make VisualClaw a natural fit for edge applications, where the cascade reduces a 1-hour streaming session from ~3,600 API uploads down to only 5-20 calls and the self-evolution makes it a perfect personalized assistant.

As Large Language Model (LLM) APIs become ubiquitous, users increasingly rely on black-box fingerprinting to verify that providers are serving the advertised premium models. However, these methods may overlook adversarial providers who manipulate model weights to cheat the fingerprint process. We introduce a novel threat termed fingerprint spoofing, where a malicious provider stealthily serves a weaker model that has been parameter-efficiently fine-tuned to mimic a stronger model, thereby evading user-side fingerprinting. We first formally prove that user-side resource constraints (i.e., finite query budgets and weak fingerprinting classifiers) make current fingerprinting vulnerable to fingerprint spoofing. Guided by this theoretical analysis, we propose GhostPrint, a cost-effective attack framework leveraging surrogate modeling, reward-ranked fine-tuning, and knowledge distillation. Extensive evaluations in both static and continual fingerprinting settings demonstrate that GhostPrint allows weak models to consistently bypass representative fingerprint methods while maintaining utility at a low fine-tuning cost, exposing a critical vulnerability in current LLM fingerprinting pipelines.

4-bit quantization significantly reduces the memory footprint and accelerates the inference of large language models (LLMs). However, its limited bit-width representation struggles to faithfully capture both dense common values (inliers) and rare large-magnitude values (outliers), causing substantial accuracy degradation. Existing mixed-precision methods mitigate this by retaining outliers in high precision, but at the cost of breaking the uniformity of low-bit execution, introducing precision conversion and extra data movement that undermine practical speedup. We propose MosaicQuant, a unified 4-bit LLM quantization paradigm built on a novel principle of inlier--outlier disaggregation. Rather than elevating outlier precision, MosaicQuant quantizes the full weight matrix into a dense 4-bit base component, where inliers are captured faithfully while outlier are inevitably quantized. A sparse 4-bit residual component is then introduced to compensate for these quantization errors, selectively targeting the most error-critical weight blocks where output distortion is shown to be concentrated. However, a unified representation alone is insufficient, as naïvely executing the sparse residual as a separate kernel still breaks the unified low-bit inference pipeline. To bridge this gap, we introduce ZipperEngine, which fuses sparse block computation into the dense 4-bit GEMM kernel via an overlapped pipeline, unifying not only the representation but also the execution into a single coherent low-bit inference pipeline. Extensive experiments on LLaMA3 and Qwen3 demonstrate that MosaicQuant preserves near-FP16 accuracy while achieving up to $1.24\times$ speedup over the W16A16 baseline.

In large language model (LLM) serving, each request accumulates persistent graphics processing unit (GPU) memory during service as its key-value cache grows with every generated token. Under high concurrency, aggregate memory usage therefore increases endogenously over time: the service process itself creates future capacity pressure. When memory capacity is exceeded, systems evict active requests, discarding cached state and restarting them later, which wastes computation and reduces throughput. We develop a discrete-time dynamical model of memory-constrained LLM inference that captures admission, memory growth, and eviction under continuous batching. In the saturated-input regime, the system admits both eviction-free fixed points and limit cycles with evictions. For homogeneous workloads, we show that the eviction-free equilibrium is unstable and that, except for a Lebesgue-measure-zero exact-capture set, the system converges to a unique worst-case limit cycle that is asymptotically stable outside this exceptional set, with throughput losses as large as 50%. For heterogeneous workloads, we prove a stability criterion in the two-class common-input setting and explain how the survival-polynomial mechanism generalizes to multiple classes and heterogeneous-input lengths. Under an input-dominated scaling regime, coprime decoding lengths stabilize the eviction-free equilibrium, while non-coprime lengths create synchronized modes that drive instability. These results characterize when workload heterogeneity desynchronizes completions and helps stabilize memory-constrained serving. More broadly, we identify service-induced congestion as a structural instability mechanism and derive scheduling design principles for sustaining high throughput.

Mechanistic interpretability seeks to explain neural network behavior by decomposing model computations into interpretable features and circuits. While transcoder-based circuit tracing has recently enabled detailed causal analyses of large language models, multimodal diffusion transformers for image generation remain comparatively opaque. We still lack tools for understanding how semantic information propagates across denoising steps and how text and image representations interact within double-stream MM-DiT architectures. Existing methods provide only partial insight: attention maps expose a limited view of token interactions, while sparse autoencoders can discover interpretable features but do not directly reveal how these features are transformed and composed through nonlinear MLP layers. In this work, we extend transcoder-based circuit tracing to multimodal diffusion transformers. We train timestep-conditioned transcoders that faithfully approximate the input-output behavior of MLP sublayers in FLUX.1[schnell]. By replacing MLPs with transcoders and linearizing the remaining computation, we obtain exact feature-to-feature attribution and recover compact, interpretable circuits. Empirically, our transcoders match or slightly outperform sparse autoencoders on the sparsity-faithfulness tradeoff. The resulting circuits reveal mechanisms underlying attribute binding and cross-stream semantic propagation, and provide causal explanations for systematic generation errors. Moreover, circuit-guided interventions are substantially more precise and effective than standard SAE-based steering. Our results demonstrate that transcoder-based circuit analysis is feasible for state-of-the-art diffusion transformers and provides a powerful framework for understanding and controlling multimodal generative models. The code is available at https://github.com/Artalmaz31/DifFRACT

While Large Language Models (LLMs) have advanced open-domain dialogue systems, maintaining long-term consistency remains a challenge due to inherent limitations in long-context reasoning and the inefficiency of processing extensive raw text. Existing approaches typically rely on either unstructured memory storage, which is prone to information loss, or computationally expensive LLMs that incur high latency. To address these limitations, we propose G-Long, a graph-enhanced framework that utilizes a fine-tuned small Language Model (sLM) for structured triplet extraction and associative retrieval, significantly reducing operational costs. Furthermore, we introduce the novel attention-aware importance scoring mechanism that leverages the intrinsic cross-attention signals of a T5 summarizer to identify salient memories. Extensive experiments across diverse benchmarks demonstrate that G-Long achieves state-of-the-art performance in both response generation and memory retrieval, yielding performance gains of up to 9.8% in response quality on MSC and 40.8% in retrieval recall on LME, while significantly minimizing computational overhead.

A skiplist is a fundamental data structure widely used in systems and applications for indexing data stores. In this work, we introduce Foresight, a cache-friendly skiplist optimization. Extending Foresight to concurrent settings introduces significant synchronization challenges that we identify and address. Foresight is a surgical optimization, easy to integrate into a wide variety of skiplist designs. We apply it to one sequential and three concurrent skiplist designs and observe throughput improvements of up to 45% in microbenchmarks. When applied to a skiplist-based index in the DBx1000 in-memory database, Foresight yields end-to-end performance gains of up to 15%.

Large reasoning models (LRMs) improve complex problem-solving by generating long intermediate reasoning traces, but this substantially increases inference costs. NVFP4 inference offers a promising approach to reduce both computational and memory costs through hardware-supported low-precision execution. However, directly applying NVFP4 to LRMs introduces two practical limitations: reasoning accuracy degrades under quantization, and existing NVFP4 kernels do not fully realize latency benefits in small-batch autoregressive decoding. In this work, we analyze the effect of NVFP4 quantization on token-level uncertainty during reasoning. We show that quantization increases incorrect sampling at low-entropy symbolic tokens, while causing over-concentration on a small set of tokens in high-uncertainty reasoning steps. Based on this observation, we propose ReSET, a reasoning-step entropy-based temperature-scaling method that estimates step-level uncertainty online and adapts the decoding temperature using both token-level and step-level entropy signals. To address the latency gap, we further design a CUDA-core small-$M$ NVFP4 kernel for latency-critical autoregressive decoding. Across reasoning benchmarks and model scales, ReSET improves NVFP4 reasoning accuracy by up to $\sim\!$2 points over the NVFP4 baseline. Our CUDA-core small-$M$ kernel further improves latency-critical decoding, delivering up to $2.5\!\times$ kernel-level speedup over NVFP4 vLLM and approximately $2\!\times$ end-to-end decoding speedup over BF16. Code is available at https://github.com/aiha-lab/ReSET.

We introduce the Trajectory-based Quantization Sensitivity Score (TQS), a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability. By modeling the network's rollout as a discrete-time dynamical system, TQS characterizes how quantization-induced errors propagate and amplify over the rollout horizon. Unlike conventional PTQ methods, where sensitivity analysis is often coupled to the quantization procedure, TQS enables a priori sensitivity estimation decoupled from quantizer selection and bit-width assignment. This separation allows for quantization budget planning even for black-box or compiled networks with fused operators. Building on this, we present TQS-PTQ, a flexible mixed-precision framework that requires no calibration data or costly second-order approximations. Our experiments show that a dynamical-systems perspective provides a robust, high-performing pathway for low-precision deployment in resource-constrained settings.

Step-level caching accelerates diffusion models by exploiting temporal redundancy across denoising steps. Existing methods make per-step cache decisions using threshold-based heuristics, without directly optimizing for final output quality. As a result, their inference latency varies across inputs and is difficult to control at deployment. In this work, we propose BudCache, which inverts this formulation: rather than letting per-step error thresholds dictate the runtime cost, we fix the compute budget in advance and search for the cache policy that best preserves the final output. To tackle the combinatorial complexity of step selection, we combine Simulated Annealing with deterministic Hill Climbing. This offline search identifies high-quality cache policies within minutes and introduces no online search or thresholding overhead during inference. When the compute budget is very tight, we further introduce cache-aware schedule alignment, which adapts the time discretization to the selected cache policy to reduce cache-induced trajectory mismatch. Experiments on FLUX.1-dev and Wan2.1 show that BudCache achieves better generation quality than heuristic caching baselines under the same inference budgets. Code is available at https://github.com/Westlake-AGI-Lab/BudCache

Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax attention makes this untenable at deployment scale. We introduce MiniMax Sparse Attention (MSA), a blockwise sparse attention built upon Grouped Query Attention (GQA). A lightweight Index Branch scores key-value blocks and independently selects a Top-k subset for each GQA group, enabling group-specific sparse retrieval while maintaining efficient block-level execution; the Main Branch then performs exact block-sparse attention over only the selected blocks. Designed around a principle of simplicity and scalability, MSA is deliberately streamlined, making it straightforward to deploy efficiently across a broad range of GPUs. To translate sparsity into practical speedups, we co-design MSA with a GPU execution path that uses exp-free Top-k selection and KV-outer sparse attention to improve tensor-core utilization under block-granular access. On a 109B-parameter model with native multimodal training, MSA performs on par with GQA while reducing per-token attention compute by 28.4x at 1M context. Paired with our co-designed kernel, MSA achieves 14.2x prefill and 7.6x decoding wall-clock speedups on H800. Our inference kernel is available at: https://github.com/MiniMax-AI/MSA. A production-grade natively multimodal model powered by MSA has been publicly released at: https://huggingface.co/MiniMaxAI/MiniMax-M3.

Code-writing large language models (CodeLLMs) generate executable code policies for embodied agents by translating natural language goals and environmental constraints into structured control programs. However, policy generation in open-domain embodied environments suffers from two fundamental limitations: (i) delayed decoding caused by repetitive prefill computation over long prompts, and (ii) limited robustness due to fully generative decoding, which often produces API mismatches, missing safety guards, and unstable control logic. To address these limitations, we present FCGraft, a Functional Cache Grafting framework. FCGraft maintains a library of function-level validated code skeletons and their associated prompt-level Transformer key-value (KV) caches, and synthesizes new policies by retrieving relevant functions and grafting their KV caches when a new task is provided. Given retrieved function caches, FCGraft performs cache grafting via stitching, which composes cached function segments into a composite policy, and patching, which locally adapts only the necessary code regions to satisfy task-specific parameters and constraints with minimal additional decoding. By eliminating redundant prefill computation, this approach reduces generation latency, while reusing validated control structures improves robustness over prompt-level caching methods RAGCache, achieving 18.31% higher task success rate and 2.3x faster policy synthesis.

Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions in model size and inference complexity. However, existing methods struggle with heavy-tailed activation distributions and therefore keep activations in high precision, fundamentally limiting end-to-end inference acceleration. To overcome this limitation, we propose TWLA, a post-training quantization (PTQ) framework that achieves 1.58-bit weight compression and 4-bit activation quantization while maintaining high accuracy. TWLA comprises three components: (1) Euclidean-to-Manifold Asymmetric Ternary Quantizer (E2M-ATQ) minimizes layer-output error under weight ternarization via a two-stage optimization from Euclidean initialization to manifold relocation; (2) Kronecker Orthogonal Tri-Modal Shaping (KOTMS) applies a Kronecker-structured orthogonal rotation to reshape weights into ternary-friendly tri-modal distributions, while the shared rotation statistically suppresses activation outliers; and (3) Inter-Layer Aware Activation Mixed Precision (ILA-AMP) explicitly introduces adjacent-layer second-order interaction costs in bit allocation and jointly optimizes for the layer-wise disparity of activation quantization gains induced by the shared orthogonal transform, preventing cascades triggered by a few weak layers. Extensive experiments demonstrate that TWLA maintains high accuracy under W1.58A4, while delivering significant inference acceleration. The code is available at <https://github.com/Kishon-zzx/TWLA>.

Right now, across the world, AI agents are repeating the same absurd act: to read one document, they each recompute it from scratch. Every agent re-runs prefill, the most compute-intensive step a large model takes, over identical text, only to rebuild a key-value (KV) cache identical to the one the agent before it just built. The same answer, computed a million times. We make a proposal that is almost offensively simple: compute it once. Let a publisher precompute a document's KV cache, and let every other agent buy the right to load it and skip prefill. It works, and it is token-exact: loading a precomputed KV and continuing matches prefilling from scratch (24/24 greedy tokens, and at the logits level), with no accuracy cost. On Qwen3-4B, reuse is 9-50x cheaper in compute than prefill, and the gap widens with length (prefill's attention scales with L^2), so a single reuse already pays it back. Then the part that matters: where the KV lives. Shipping it fails, because KV is nearly incompressible, so per-load egress costs more than the prefill it saves. Hosting it provider-side, exactly as production prompt-caching works, removes egress entirely. The size of the prize is set by our measured compute saving: serving one hot 3774-token document to 80M agents costs ~$1.5M to re-prefill but only ~$0.03M of reuse compute (49.7x less). The 0.1x cache-read tariff APIs charge passes a 10x discount to users while sitting inside this measured envelope, so the 10x is a floor that the measured ~50x compute saving clears, and the gap to the physical ~50x is provider margin: millions of dollars per popular document. We frame the resulting agent-native prefill CDN and leave lossless KV compression and a cross-party payment layer as the open problems.

Retrieval-augmented and agentic workloads repeatedly prefill recurring predictable structured inputs (which we call "spans") such as documents and code files. Yet, prefix caching in engines such as vLLM cannot reuse their KV entries unless they share identical prefixes with another request, while Position-Independent Caching (PIC) implementations within production-grade inference servers typically either require substantial server code changes or keep KV state outside the server, incurring host-to-device transfer overhead. We present Minimalistic PIC (MiniPIC): a minimal, flexible and fast vLLM design built from two ingredients: positional-encoding-free KV cache and user-controlled cache-reuse primitives. MiniPIC stores unrotated K vectors in the KV cache, applies RoPE to K tiles inside attention using per-request logical positions, and exposes three user-facing and token-level primitives: block-aligned padding, span separator (SSep), and prompt depend (PDep), that modify hashing behavior and effective block-level causal attention structure. With fewer than 100 lines of core-engine changes plus a custom attention backend, these primitives are sufficient to realize multiple PIC methods, including Block-Attention, EPIC, and Prompt Cache, within the same running vLLM instance, while natively integrating with KV cache CPU offload implementations. On 2WikiMultihopQA, MiniPIC with interleaved scheduling improves prefill throughput by 49% over baseline vLLM, reduces cached-span time-to-first-token by up to two orders of magnitude, preserves the linear prefill scaling of uncached spans, and incurs only 5.7% worst-case overhead.

Semantic mapping is a core service that enables grounded interactions in emerging Extended Reality (XR) applications such as AI assistants and spatial object search. Deploying this capability on mobile XR devices requires a system that is open-vocabulary, real-time, and low-power. Existing approaches are compute-intensive and assume server-class resources. Cloud offloading offers a practical path, but no existing system splits semantic mapping across the device-cloud boundary or manages its communication, execution, and memory footprint. We present SemanticXR, the first device-cloud system for real-time, open-vocabulary semantic mapping and querying under XR power, bandwidth, and memory constraints. Our key insight is to elevate semantically identifiable objects to first-class units of communication, execution, and memory across the device and server. On the server, object-level parallelism and geometry downsampling improve mapping latency, while object-level depth-mapping co-design reduces upstream bandwidth. On the device, an object-level sparse local map with incremental updates and update prioritization enables network-robust querying with bounded memory and downstream bandwidth. Object-level configurable resource usage vs. quality trade-offs let applications and the system adapt mapping to application requirements and operating conditions, respectively. Against a device-cloud baseline with the same perception models, object-level organization improves server-side mapping latency by 2.2X at equal semantic quality. Depth-mapping co-design maintains upstream bandwidth under 2.5 Mbps. On the device, SemanticXR sustains sub-100 ms query latency for up to 10,000 objects even under network drops, supports tens of thousands of objects within 500 MB, and scales downstream bandwidth with map changes, not total scene size. The system adds only 2% device power during normal operation.

Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving. Existing systems assign each request a fixed parallel configuration throughout its lifetime. However, DiT workloads exhibit substantial heterogeneity across requests, execution stages, and system conditions, making static parallelism inefficient and often leading to poor GPU utilization and degraded service quality. This paper argues that DiT serving should treat GPU parallelism as a first-class schedulable resource. We present GF-DiT, a policy-programmable runtime for elastic DiT serving that dynamically adapts the parallelism of running requests according to workload demands and service objectives. GF-DiT introduces an asynchronous execution abstraction that decomposes requests into independently schedulable trajectory tasks and enables online GPU reallocation. To make elastic parallelism practical, GF-DiT further proposes group-free collectives, a lightweight communication abstraction that supports low-overhead online formation and reconfiguration of arbitrary execution groups. We implement GF-DiT in vLLM-Omni and evaluate it on representative image and video diffusion workloads. Compared with fixed-pipeline execution with static parallelism, GF-DiT improves throughput by up to 6.01$\times$, reduces mean latency by up to 95%, lowers SLO violation rates by up to 90%, and reduces communication-group setup overhead from 778 ms to approximately 60 $μ$s.

Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts, quality degradation, and temporal drift. In this paper, we propose TetherCache, a training-free and plug-and-play cache management strategy for drift-resistant long video generation. TetherCache organizes the cache into sink, memory, and recent regions, and introduces two complementary mechanisms. First, GRAB (Gated Recall with Attention-Diversity Balancing) selects long-range memory frames using a gated score that combines attention-based relevance with temporal diversity, preserving informative yet diverse historical context under a fixed cache budget. Second, TAME (Trusted Alignment via Memory Editing) lightly edits newly recalled memory tokens by aligning their statistics to a trusted context distribution, reducing the pollution caused by drifted historical features. Built on Self-Forcing, TetherCache consistently improves long-video generation quality on VBench-Long across 30s, 60s, and 240s settings. In particular, for 240s generation, it substantially improves overall and semantic scores while reducing quality drift from 7.84 to 1.33, demonstrating its effectiveness for stable long-horizon autoregressive video diffusion.

Arbor is a multi-agent framework that introduces structured tree search as a cognition layer for autonomous agents operating in large, stateful action spaces. Prior autonomous optimization systems operate on isolated targets with stateless evaluation. Arbor instead maintains an explicit search tree of scored hypotheses that serves as the shared working memory across agents, evolving with every measurement, treating failures as diagnostic signal that reshapes subsequent exploration, and expanding as prior successes shift the bottleneck distribution. We validate Arbor on full-stack LLM inference optimization, a domain where achieving peak performance has historically required coordinated effort from engineering teams across the application, framework, compiler, kernel, and hardware stack. Arbor pairs an Orchestrator agent, which drives optimization by delegating to Domain Specialists across the inference stack, with a Critic agent that safeguards stability through root-cause analysis, introspection, and measurement validation — a checks-and-balances architecture where neither agent can unilaterally drive the system. Agent capabilities are decomposed into hard skills (domain expertise) and soft skills (coordination protocols that determine how contributions compose), enabling fully autonomous multi-day campaigns. Arbor achieves up to 193% inference throughput-latency Pareto improvement over vendor-optimized baselines, while a single agent without the harness plateaus at +33% throughput improvement and crashes irrecoverably within hours. Arbor generalizes to multiple generations of hardware platform, and run-to-run variance is within 2 percentage points demonstrating that the method is hardware-agnostic and reproducible.