Daily Papers

Recent breakthroughs in video diffusion models have significantly accelerated the development of video editing techniques. However, existing methods often rely on inpainting video frames based on masked input, which requires extracting the target video mask in advance, and the precision of the segmentation directly affects the quality of the completion. In this paper, we present SEDiT, a novel one-stage video Subtitle Erasure approach via One-step Diffusion Transformer. We introduce a mask-free inference approach that enables direct erasure of the targeted subtitle. The proposed one-stage framework mitigates the sub-optimality inherent in the two-stage processing of prior models. Since subtitle removal is a localized editing task in which most pixels remain unchanged, the underlying distribution shift is minimal, making it well-suited to one-step generation under rectified flow. We empirically validate the reliability of one-step denoising and further provide a formal theoretical justification. Under the localized-editing structure of subtitle removal, the conditional optimal transport (OT) map and its induced rectified flow velocity field are Lipschitz continuous with respect to the latent variable, which underpins the theoretical feasibility of one-step sampling. To address the challenge of long-term temporal consistency, we adopt a hybrid training strategy by occasionally conditioning the model with a clean first-frame latent. This facilitates temporal continuity, allowing each segment during inference to leverage the output of its predecessor. To avoid visible seams caused by cropping and reinserting processed targets, particularly in scenarios involving substantial motion, we feed the original video directly into SEDiT. Thanks to one-step and chunk-wise streaming inference, our method can efficiently handle native 1440p video with infinite length.

Real-time portrait animation is essential for interactive applications such as virtual assistants and live avatars, requiring high visual fidelity, temporal coherence, ultra-low latency, and responsive control from dynamic inputs like reference images and driving signals. While diffusion-based models achieve strong quality, their non-causal nature hinders streaming deployment. Causal autoregressive video generation approaches enable efficient frame-by-frame generation but suffer from error accumulation, motion discontinuities at chunk boundaries, and degraded long-term consistency. In this work, we present a novel streaming framework named Knot Forcing for real-time portrait animation that addresses these challenges through three key designs: (1) a chunk-wise generation strategy with global identity preservation via cached KV states of the reference image and local temporal modeling using sliding window attention; (2) a temporal knot module that overlaps adjacent chunks and propagates spatio-temporal cues via image-to-video conditioning to smooth inter-chunk motion transitions; and (3) A "running ahead" mechanism that dynamically updates the reference frame's temporal coordinate during inference, keeping its semantic context ahead of the current rollout frame to support long-term coherence. Knot Forcing enables high-fidelity, temporally consistent, and interactive portrait animation over infinite sequences, achieving real-time performance with strong visual stability on consumer-grade GPUs.

Zero-shot voice conversion (VC) aims to convert a source utterance into the voice of an unseen target speaker while preserving its linguistic content. Although recent systems have improved conversion quality, building zero-shot VC systems for interactive scenarios remains challenging because high-fidelity speaker transfer and low-latency streaming inference are difficult to achieve simultaneously. In this work, we present X-VC, a zero-shot streaming VC system that performs one-step conversion in the latent space of a pretrained neural codec. X-VC uses a dual-conditioning acoustic converter that jointly models source codec latents and frame-level acoustic conditions derived from target reference speech, while injecting utterance-level target speaker information through adaptive normalization. To reduce the mismatch between training and inference, we train the model with generated paired data and a role-assignment strategy that combines standard, reconstruction, and reversed modes. For streaming inference, we further adopt a chunkwise inference scheme with overlap smoothing that is aligned with the segment-based training paradigm of the codec. Experiments on Seed-TTS-Eval show that X-VC achieves the best streaming WER in both English and Chinese, strong speaker similarity in same-language and cross-lingual settings, and substantially lower offline real-time factor than the compared baselines. These results suggest that codec-space one-step conversion is a practical approach for building high-quality low-latency zero-shot VC systems. Audio samples are available at https://x-vc.github.io. Our code and checkpoints will also be released.

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality). Streaming context incrementally--overlapping retrieval with inference--can mitigate this latency, but doing so with concurrent requests introduces new challenges: requests contend for GPU compute and memory, and scheduling must adapt to dynamic context arrivals. We present Stream2LLM, a streaming-aware LLM serving system for concurrent prefill-decode disaggregated deployments. Stream2LLM introduces adaptive scheduling and preemption for two distinct retrieval patterns: append-mode (progressive context accumulation) and update-mode (iterative refinement with cache invalidation). It decouples scheduling decisions from resource acquisition, enabling flexible preemption strategies guided by hardware-specific cost models, and uses longest common prefix matching to minimize redundant computation when input changes dynamically. To evaluate Stream2LLM, we collect two large-scale, real-world streaming workloads based on web crawling and approximate nearest neighbor search. Our evaluation demonstrates that streaming architecture delivers up to 11x TTFT improvements, with cost-aware scheduling providing critical benefits under memory pressure, all while maintaining throughput parity with non-streaming baselines. Code: https://github.com/rajveerb/stream2llm/tree/mlsys_artifact

Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model. While effective, in application-specific settings, it often involves fine-tuning both draft and target models to achieve high acceptance rates. As the number of downstream tasks grows, these draft models add significant complexity to inference systems. We propose Speculative Streaming, a single-model speculative decoding method that fuses drafting into the target model by changing the fine-tuning objective from next token prediction to future n-gram prediction. Speculative Streaming speeds up decoding by 1.8 - 3.1X in a diverse set of tasks, such as Summarization, Structured Queries, and Meaning Representation, without sacrificing generation quality. Additionally, Speculative Streaming is parameter-efficient. It achieves on-par/higher speed-ups than Medusa-style architectures while using ~10000X fewer extra parameters, making it well-suited for resource-constrained devices.

Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models. While recent works have accelerated inference via KV cache reuse or heuristic decoding, they overlook the intrinsic inefficiencies within the block-wise diffusion process. Specifically, they suffer from spatial redundancy by modeling informative-sparse suffix regions uniformly and temporal inefficiency by applying fixed denoising schedules across all the decoding process. To address this, we propose Streaming-dLLM, a training-free framework that streamlines inference across both spatial and temporal dimensions. Spatially, we introduce attenuation guided suffix modeling to approximate the full context by pruning redundant mask tokens. Temporally, we employ a dynamic confidence aware strategy with an early exit mechanism, allowing the model to skip unnecessary iterations for converged tokens. Extensive experiments show that Streaming-dLLM achieves up to 68.2X speedup while maintaining generation quality, highlighting its effectiveness in diffusion decoding. The code is available at https://github.com/xiaoshideta/Streaming-dLLM.

Existing zero-shot text-to-speech (TTS) systems are typically designed to process complete sentences and are constrained by the maximum duration for which they have been trained. However, in many streaming applications, texts arrive continuously in short chunks, necessitating instant responses from the system. We identify the essential capabilities required for chunk-level streaming and introduce LiveSpeech 2, a stream-aware model that supports infinitely long speech generation, text-audio stream synchronization, and seamless transitions between short speech chunks. To achieve these, we propose (1) adopting Mamba, a class of sequence modeling distinguished by linear-time decoding, which is augmented by cross-attention mechanisms for conditioning, (2) utilizing rotary positional embeddings in the computation of cross-attention, enabling the model to process an infinite text stream by sliding a window, and (3) decoding with semantic guidance, a technique that aligns speech with the transcript during inference with minimal overhead. Experimental results demonstrate that our models are competitive with state-of-the-art language model-based zero-shot TTS models, while also providing flexibility to support a wide range of streaming scenarios.

Learning-based 3D visual geometry models have benefited substantially from large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention for strong streaming reconstruction, but suffers from unbounded KV cache growth, leading to escalating memory consumption and inference latency as input frames accumulate. We propose XStreamVGGT, a tuning-free approach that systematically compresses the KV cache through joint pruning and quantization, enabling extremely memory-efficient streaming inference. Specifically, redundant KVs originating from multi-view inputs are pruned through efficient token importance identification, enabling a fixed memory budget. Leveraging the unique distribution of KV tensors, we incorporate KV quantization to further reduce memory consumption. Extensive evaluations show that XStreamVGGT achieves mostly negligible performance degradation while substantially reducing memory usage by 4.42times and accelerating inference by 5.48times, enabling scalable and practical streaming 3D applications. The code is available at https://github.com/ywh187/XStreamVGGT/.

Large language models (LLMs) have demonstrated remarkable capabilities in chain of thought (CoT) reasoning. However, the current LLM reasoning paradigm initiates thinking only after the entire input is available, which introduces unnecessary latency and weakens attention to earlier information in dynamic scenarios. Inspired by human cognition of thinking while reading, we first design a \textbf{streaming thinking} paradigm for LLMs, where reasoning unfolds in the order of input and further adjusts its depth once reading is complete. We instantiate this paradigm with StreamingThinker, a framework that enables LLMs to think while reading through the integration of streaming CoT generation, streaming-constraint training, and streaming parallel inference. Specifically, StreamingThinker employs streaming reasoning units with quality control for CoT generation, enforces order-preserving reasoning through streaming attention masks and position encoding, and leverages parallel KV caches that decouple input encoding from reasoning generation, thereby ensuring alignment and enabling true concurrency. We evaluate StreamingThinker on the Qwen3 model family across math reasoning, logical reasoning, and context-based QA reasoning tasks. Experimental results show that the StreamingThinker preserves performance comparable to batch thinking, while yielding an 80\% reduction in token waiting before the onset of reasoning and a more than 60\% reduction in time-level latency for producing the final answer, demonstrating the effectiveness of the streaming paradigm for LLM reasoning. Code is publicly available at https://github.com/EIT-NLP/StreamingLLM/tree/main/StreamingThinker.

Deploying Large Language Models (LLMs) in streaming applications such as multi-round dialogue, where long interactions are expected, is urgently needed but poses two major challenges. Firstly, during the decoding stage, caching previous tokens' Key and Value states (KV) consumes extensive memory. Secondly, popular LLMs cannot generalize to longer texts than the training sequence length. Window attention, where only the most recent KVs are cached, is a natural approach -- but we show that it fails when the text length surpasses the cache size. We observe an interesting phenomenon, namely attention sink, that keeping the KV of initial tokens will largely recover the performance of window attention. In this paper, we first demonstrate that the emergence of attention sink is due to the strong attention scores towards initial tokens as a ``sink'' even if they are not semantically important. Based on the above analysis, we introduce StreamingLLM, an efficient framework that enables LLMs trained with a finite length attention window to generalize to infinite sequence lengths without any fine-tuning. We show that StreamingLLM can enable Llama-2, MPT, Falcon, and Pythia to perform stable and efficient language modeling with up to 4 million tokens and more. In addition, we discover that adding a placeholder token as a dedicated attention sink during pre-training can further improve streaming deployment. In streaming settings, StreamingLLM outperforms the sliding window recomputation baseline by up to 22.2x speedup. Code and datasets are provided at https://github.com/mit-han-lab/streaming-llm.

Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style process misaligned with real-world video streams where information arrives sequentially. Motivated by the streaming nature of video data, we investigate two streaming reasoning paradigms for LVLMs. The first, an interleaved paradigm, alternates between receiving frames and producing partial reasoning but remains constrained by strictly ordered cache updates. To better match streaming inputs, we propose Think-as-You-See (TaYS), a unified framework enabling true concurrent reasoning. TaYS integrates parallelized CoT generation, stream-constrained training, and stream-parallel inference. It further employs temporally aligned reasoning units, streaming attention masks and positional encodings, and a dual KV-cache that decouples visual encoding from textual reasoning. We evaluate all paradigms on the Qwen2.5-VL family across representative video CoT tasks, including event dynamics analysis, causal reasoning, and thematic understanding. Experiments show that TaYS consistently outperforms both batch and interleaved baselines, improving reasoning performance while substantially reducing time-to-first-token (TTFT) and overall reasoning delay. These results demonstrate the effectiveness of data-aligned streaming reasoning in enabling efficient and responsive video understanding for LVLMs. We release our code at https://github.com/EIT-NLP/StreamingLLM/tree/main/TaYS{this repository.}

Long context fine-tuning of large language models(LLMs) involves training on datasets that are predominantly composed of short sequences and a small proportion of longer sequences. However, existing approaches overlook this long-tail distribution and employ training strategies designed specifically for long sequences. Moreover, these approaches also fail to address the challenges posed by variable sequence lengths during distributed training, such as load imbalance in data parallelism and severe pipeline bubbles in pipeline parallelism. These issues lead to suboptimal training performance and poor GPU resource utilization. To tackle these problems, we propose a chunk-centric training method named ChunkFlow. ChunkFlow reorganizes input sequences into uniformly sized chunks by consolidating short sequences and splitting longer ones. This approach achieves optimal computational efficiency and balance among training inputs. Additionally, ChunkFlow incorporates a state-aware chunk scheduling mechanism to ensure that the peak memory usage during training is primarily determined by the chunk size rather than the maximum sequence length in the dataset. Integrating this scheduling mechanism with existing pipeline scheduling algorithms further enhances the performance of distributed training. Experimental results demonstrate that, compared with Megatron-LM, ChunkFlow can be up to 4.53x faster in the long context fine-tuning of LLMs. Furthermore, we believe that ChunkFlow serves as an effective solution for a broader range of scenarios, such as long context continual pre-training, where datasets contain variable-length sequences.

Conventional transformer inference engines are request-driven, paying an O(n) prefill cost on every query. In streaming workloads, where data arrives continuously and queries probe an ever-growing context, this cost is prohibitive. We introduce a data-driven computational model centred on stateful sessions: a persistent KV cache advanced incrementally as new data arrives, so prefill is moved off the critical path and query latency becomes O(|q|), independent of accumulated context size. Building on this, Flash Queries reclaim idle GPU cycles between data arrivals to pre-evaluate registered questions and return cached answers before the user asks, a pattern that is structurally impossible in stateless engines because they discard intermediate state between requests. A multi-tenant continuous-batching scheduler with cell-budget admission and prefix-aware grouped prefill lets dozens of stateful sessions coexist on a single GPU while preserving full quadratic self-attention. On streaming market-data benchmarks the reference implementation achieves up to 5.9x speedup over conventional inference engines (vLLM, SGLang, TensorRT-LLM, llama.cpp), holding query latency constant as accumulated context grows.

Attention efficiency is critical to large language model (LLM) inference. While prior advances optimize attention execution for individual requests (e.g., FlashAttention), production LLM serving relies on batching requests with highly heterogeneous sequence lengths for high serving throughput. This mismatch induces severe computation and I/O imbalance, exacerbates stragglers, and underutilizes GPU resources. We present PackInfer, a kernel-level attention framework that enables compute- and I/O-aware execution for heterogeneous batched inference. PackInfer orchestrates batched requests into load-balanced execution groups, effectively saturating GPU utilization by packing multiple requests into unified kernel launches. By constructing attention kernels directly over packed query-key regions, PackInfer eliminates redundant computation and balances thread-block execution. It then incorporates I/O-aware grouping that co-locates shared-prefix requests and reorganizes KV caches into group-contiguous layouts, reducing memory fragmentation and redundant data movement as generation evolves. Evaluations on real-world workloads show that PackInfer reduces inference latency by 13.0-20.1%, and improves throughput by 20% compared to the state-of-the-art FlashAttention.

Recently, there has been an increasing interest in unifying streaming and non-streaming speech recognition models to reduce development, training and deployment cost. The best-known approaches rely on either window-based or dynamic chunk-based attention strategy and causal convolutions to minimize the degradation due to streaming. However, the performance gap still remains relatively large between non-streaming and a full-contextual model trained independently. To address this, we propose a dynamic chunk-based convolution replacing the causal convolution in a hybrid Connectionist Temporal Classification (CTC)-Attention Conformer architecture. Additionally, we demonstrate further improvements through initialization of weights from a full-contextual model and parallelization of the convolution and self-attention modules. We evaluate our models on the open-source Voxpopuli, LibriSpeech and in-house conversational datasets. Overall, our proposed model reduces the degradation of the streaming mode over the non-streaming full-contextual model from 41.7% and 45.7% to 16.7% and 26.2% on the LibriSpeech test-clean and test-other datasets respectively, while improving by a relative 15.5% WER over the previous state-of-the-art unified model.

While video streaming understanding has made significant strides, real-world applications, such as live sports broadcasting, autonomous driving, and multi-screen collaboration, inherently demand continuous, multi-stream interactions. However, existing benchmarks are confined to single-stream paradigms, leaving a critical gap in evaluating online, cross-stream reasoning. To bridge this, we introduce X-Stream, the first benchmark dedicated to multi-stream streaming understanding. Comprising 4,220 rigorously curated QA pairs across 932 videos, X-Stream evaluates 11 subtasks across multi-window, multi-view, and multi-device scenarios. Crucially, our dataset is constructed using a novel dual-verification pipeline that prevents over-reliance on a single stream. Furthermore, we pioneer the conceptualization of multi-modal large language models (MLLMs) as naive multiplexers, systematically evaluating their performance through the lens of Signal Multiplexing Theory. Our extensive online inference experiments reveal a stark reality: state-of-the-art MLLMs struggle significantly with concurrent streams, achieving only about 50% score and exhibiting poor proactive ability. Ultimately, X-Stream exposes the trade-off of current multiplexing schemes, providing both a practical evaluation protocol and empirical guidance for next-generation multi-stream agents.

Deep learning time-series processing often relies on convolutional neural networks with overlapping windows. This overlap allows the network to produce an output faster than the window length. However, it introduces additional computations. This work explores the potential to optimize computational efficiency during inference by exploiting convolution's shift-invariance properties to skip the calculation of layer activations between successive overlapping windows. Although convolutions are shift-invariant, zero-padding and pooling operations, widely used in such networks, are not efficient and complicate efficient streaming inference. We introduce StreamiNNC, a strategy to deploy Convolutional Neural Networks for online streaming inference. We explore the adverse effects of zero padding and pooling on the accuracy of streaming inference, deriving theoretical error upper bounds for pooling during streaming. We address these limitations by proposing signal padding and pooling alignment and provide guidelines for designing and deploying models for StreamiNNC. We validate our method in simulated data and on three real-world biomedical signal processing applications. StreamiNNC achieves a low deviation between streaming output and normal inference for all three networks (2.03 - 3.55% NRMSE). This work demonstrates that it is possible to linearly speed up the inference of streaming CNNs processing overlapping windows, negating the additional computation typically incurred by overlapping windows.

Large language models (LLMs) have achieved impressive success, but their high memory requirements present challenges for long-context token generation. In this paper we study the streaming complexity of attention approximation, a key computational primitive underlying token generation. Our main contribution is BalanceKV, a streaming algorithm for epsilon-approximating attention computations based on geometric process for selecting a balanced collection of Key and Value tokens as per Banaszczyk's vector balancing theory. We complement our algorithm with space lower bounds for streaming attention computation. Besides strong theoretical guarantees, BalanceKV exhibits empirically validated performance improvements over existing methods, both for attention approximation and end-to-end performance on various long context benchmarks.

Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video question answering (VQA). Existing state-of-the-art approaches rely on key-value caching to accumulate frame-level information over time, but use a limited number of tokens per frame, leading to the loss of fine-grained visual details. In this work, we propose scaling the token budget to enable more granular spatiotemporal understanding and reasoning. First, we find that current methods are ill-equipped to handle dense streams: their feature encoding causes query-frame similarity scores to increase over time, biasing retrieval toward later frames. To address this, we introduce an adaptive selection strategy that reduces token redundancy while preserving local spatiotemporal information. We further propose a training-free retrieval mixture-of-experts that leverages external models to better identify relevant frames. Our method, MemStream, achieves +8.0% on CG-Bench, +8.5% on LVBench, and +2.4% on VideoMME (Long) over ReKV with Qwen2.5-VL-7B.

Recent advances in Large Language Models (LLMs) have enabled the development of Video-LLMs, advancing multimodal learning by bridging video data with language tasks. However, current video understanding models struggle with processing long video sequences, supporting multi-turn dialogues, and adapting to real-world dynamic scenarios. To address these issues, we propose StreamChat, a training-free framework for streaming video reasoning and conversational interaction. StreamChat leverages a novel hierarchical memory system to efficiently process and compress video features over extended sequences, enabling real-time, multi-turn dialogue. Our framework incorporates a parallel system scheduling strategy that enhances processing speed and reduces latency, ensuring robust performance in real-world applications. Furthermore, we introduce StreamBench, a versatile benchmark that evaluates streaming video understanding across diverse media types and interactive scenarios, including multi-turn interactions and complex reasoning tasks. Extensive evaluations on StreamBench and other public benchmarks demonstrate that StreamChat significantly outperforms existing state-of-the-art models in terms of accuracy and response times, confirming its effectiveness for streaming video understanding. Code is available at StreamChat: https://github.com/hmxiong/StreamChat.

Real-time understanding of continuous video streams is essential for interactive assistants and multimodal agents operating in dynamic environments. However, most existing video reasoning approaches follow a batch paradigm that defers reasoning until the full video context is observed, resulting in high latency and growing computational cost that are incompatible with streaming scenarios. In this paper, we introduce ThinkStream, a framework for streaming video reasoning based on a Watch--Think--Speak paradigm that enables models to incrementally update their understanding as new video observations arrive. At each step, the model performs a short reasoning update and decides whether sufficient evidence has accumulated to produce a response. To support long-horizon streaming, we propose Reasoning-Compressed Streaming Memory (RCSM), which treats intermediate reasoning traces as compact semantic memory that replaces outdated visual tokens while preserving essential context. We further train the model using a Streaming Reinforcement Learning with Verifiable Rewards scheme that aligns incremental reasoning and response timing with the requirements of streaming interaction. Experiments on multiple streaming video benchmarks show that ThinkStream significantly outperforms existing online video models while maintaining low latency and memory usage. Code, models and data will be released at https://github.com/johncaged/ThinkStream

Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio, thanks to their temporally uni-directional attention mechanism, which models correlations between the current token and previous tokens. However, video streaming remains much less explored, despite a growing need for live video processing. State-of-the-art video diffusion models leverage bi-directional temporal attention to model the correlations between the current frame and all the surrounding (i.e. including future) frames, which hinders them from processing streaming videos. To address this problem, we present Live2Diff, the first attempt at designing a video diffusion model with uni-directional temporal attention, specifically targeting live streaming video translation. Compared to previous works, our approach ensures temporal consistency and smoothness by correlating the current frame with its predecessors and a few initial warmup frames, without any future frames. Additionally, we use a highly efficient denoising scheme featuring a KV-cache mechanism and pipelining, to facilitate streaming video translation at interactive framerates. Extensive experiments demonstrate the effectiveness of the proposed attention mechanism and pipeline, outperforming previous methods in terms of temporal smoothness and/or efficiency.

Large Language Models (LLMs) are primarily designed for batch processing. Existing methods for adapting LLMs to streaming rely either on expensive re-encoding or specialized architectures with limited scalability. This work identifies three key mismatches in adapting batch-oriented LLMs to streaming: (1) input-attention, (2) output-attention, and (3) position-ID mismatches. While it is commonly assumed that the latter two mismatches require frequent re-encoding, our analysis reveals that only the input-attention mismatch significantly impacts performance, indicating re-encoding outputs is largely unnecessary. To better understand this discrepancy with the common assumption, we provide the first comprehensive analysis of the impact of position encoding on LLMs in streaming, showing that preserving relative positions within source and target contexts is more critical than maintaining absolute order. Motivated by the above analysis, we introduce a group position encoding paradigm built on batch architectures to enhance consistency between streaming and batch modes. Extensive experiments on cross-lingual and cross-modal tasks demonstrate that our method outperforms existing approaches. Our method requires no architectural modifications, exhibits strong generalization in both streaming and batch modes. The code is available at repository https://github.com/EIT-NLP/StreamingLLM.

Chunking strategies significantly impact the effectiveness of Retrieval-Augmented Generation (RAG) systems. Existing methods operate within fixed-granularity paradigms that rely on static boundary identification, limiting their adaptability to diverse query requirements. This paper presents FreeChunker, a Cross-Granularity Encoding Framework that fundamentally transforms the traditional chunking paradigm: the framework treats sentences as atomic units and shifts from static chunk segmentation to flexible retrieval supporting arbitrary sentence combinations. This paradigm shift not only significantly reduces the computational overhead required for semantic boundary detection but also enhances adaptability to complex queries. Experimental evaluation on LongBench V2 demonstrates that FreeChunker achieves superior retrieval performance compared to traditional chunking methods, while significantly outperforming existing approaches in computational efficiency.

End-to-end automatic speech recognition systems represent the state of the art, but they rely on thousands of hours of manually annotated speech for training, as well as heavyweight computation for inference. Of course, this impedes commercialization since most companies lack vast human and computational resources. In this paper, we explore training and deploying an ASR system in the label-scarce, compute-limited setting. To reduce human labor, we use a third-party ASR system as a weak supervision source, supplemented with labeling functions derived from implicit user feedback. To accelerate inference, we propose to route production-time queries across a pool of CUDA graphs of varying input lengths, the distribution of which best matches the traffic's. Compared to our third-party ASR, we achieve a relative improvement in word-error rate of 8% and a speedup of 600%. Our system, called SpeechNet, currently serves 12 million queries per day on our voice-enabled smart television. To our knowledge, this is the first time a large-scale, Wav2vec-based deployment has been described in the academic literature.

Efficient inference for on-device Large Language Models (LLMs) remains challenging due to limited hardware resources and the high cost of the prefill stage, which processes the full input context to construct Key-Value (KV) caches. We present SparKV, an adaptive KV loading framework that combines cloud-based KV streaming with on-device computation. SparKV models the cost of individual KV chunks and decides whether each chunk should be streamed or computed locally, while overlapping the two execution paths to reduce latency. To handle fluctuations in wireless connectivity and edge resource availability, SparKV further refines offline-generated schedules at runtime to rebalance communication and computation costs. Experiments across diverse datasets, LLMs, and edge devices show that SparKV reduces Time-to-First-Token by 1.3$x-5.1x with negligible impact on response quality, while lowering per-request energy consumption by 1.5x to 3.3x, demonstrating its robustness and practicality for real-world on-device deployment.

The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive. To address this challenge, various approaches aim to retain critical portions of the context to optimally approximate Full Attention (FA) through Key-Value (KV) compression or Sparse Attention (SA), enabling the processing of virtually unlimited text lengths in a streaming manner. However, these methods struggle to achieve performance levels comparable to FA, particularly in retrieval tasks. In this paper, our analysis of attention head patterns reveals that LLMs' attention distributions show strong local correlations, naturally reflecting a chunking mechanism for input context. We propose Ltri-LLM framework, which divides KVs into spans, stores them in an offline index, and retrieves the relevant KVs into memory for various queries. Experimental results on popular long text benchmarks show that Ltri-LLM can achieve performance close to FA while maintaining efficient, streaming-based inference.

With the explosive growth of livestream broadcasting, there is an urgent need for new summarization technology that enables us to create a preview of streamed content and tap into this wealth of knowledge. However, the problem is nontrivial due to the informal nature of spoken language. Further, there has been a shortage of annotated datasets that are necessary for transcript summarization. In this paper, we present StreamHover, a framework for annotating and summarizing livestream transcripts. With a total of over 500 hours of videos annotated with both extractive and abstractive summaries, our benchmark dataset is significantly larger than currently existing annotated corpora. We explore a neural extractive summarization model that leverages vector-quantized variational autoencoder to learn latent vector representations of spoken utterances and identify salient utterances from the transcripts to form summaries. We show that our model generalizes better and improves performance over strong baselines. The results of this study provide an avenue for future research to improve summarization solutions for efficient browsing of livestreams.

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with full attention leads to quadratic computational costs and poor performance on long videos. Meanwhile, simple sliding window methods are also flawed, as they either break coherence or suffer from high latency due to redundant recomputation. In this paper, we introduce StreamingVLM, a model designed for real-time, stable understanding of infinite visual input. Our approach is a unified framework that aligns training with streaming inference. During inference, we maintain a compact KV cache by reusing states of attention sinks, a short window of recent vision tokens, and a long window of recent text tokens. This streaming ability is instilled via a simple supervised fine-tuning (SFT) strategy that applies full attention on short, overlapped video chunks, which effectively mimics the inference-time attention pattern without training on prohibitively long contexts. For evaluation, we build Inf-Streams-Eval, a new benchmark with videos averaging over two hours that requires dense, per-second alignment between frames and text. On Inf-Streams-Eval, StreamingVLM achieves a 66.18% win rate against GPT-4O mini and maintains stable, real-time performance at up to 8 FPS on a single NVIDIA H100. Notably, our SFT strategy also enhances general VQA abilities without any VQA-specific fine-tuning, improving performance on LongVideoBench by +4.30 and OVOBench Realtime by +5.96. Code is available at https://github.com/mit-han-lab/streaming-vlm.

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming (online or real-time) transcription, due to limitations in their architecture and training methodology. We propose a method to turn the transformer encoder-decoder model into a low-latency streaming model that is careless about future context. We present an analysis explaining why it is not straightforward to convert an encoder-decoder transformer to a low-latency streaming model. Our proposed method modifies the existing (non-causal) encoder to a causal encoder by fine-tuning both the encoder and decoder using Low-Rank Adaptation (LoRA) and a weakly aligned dataset. We then propose an updated inference mechanism that utilizes the fine-tune causal encoder and decoder to yield greedy and beam-search decoding, and is shown to be locally optimal. Experiments on low-latency chunk sizes (less than 300 msec) show that our fine-tuned model outperforms existing non-fine-tuned streaming approaches in most cases, while using a lower complexity. Additionally, we observe that our training process yields better alignment, enabling a simple method for extracting word-level timestamps. We release our training and inference code, along with the fine-tuned models, to support further research and development in streaming ASR.

Transformer-based embedding models suffer from quadratic computational and linear memory complexity, limiting their utility for long sequences. We propose recurrent architectures as an efficient alternative, introducing a vertically chunked inference strategy that enables fast embedding generation with memory usage that becomes constant in the input length once it exceeds the vertical chunk size. By fine-tuning Mamba2 models, we demonstrate their viability as general-purpose text embedders, achieving competitive performance across a range of benchmarks while maintaining a substantially smaller memory footprint compared to transformer-based counterparts. We empirically validate the applicability of our inference strategy to Mamba2, RWKV, and xLSTM models, confirming consistent runtime-memory trade-offs across architectures and establishing recurrent models as a compelling alternative to transformers for efficient embedding generation.

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 LLM and VLM benchmarks demonstrate consistent gains over prior methods under comparable efficiency budgets.

Autoregressive models, despite their commendable performance in a myriad of generative tasks, face challenges stemming from their inherently sequential structure. Inference on these models, by design, harnesses a temporal dependency, where the current token's probability distribution is conditioned on preceding tokens. This inherent characteristic severely impedes computational efficiency during inference as a typical inference request can require more than thousands of tokens, where generating each token requires a load of entire model weights, making the inference more memory-bound. The large overhead becomes profound in real deployment where requests arrive randomly, necessitating various generation lengths. Existing solutions, such as dynamic batching and concurrent instances, introduce significant response delays and bandwidth contention, falling short of achieving optimal latency and throughput. To address these shortcomings, we propose Flover -- a temporal fusion framework for efficiently inferring multiple requests in parallel. We deconstruct the general generation pipeline into pre-processing and token generation, and equip the framework with a dedicated work scheduler for fusing the generation process temporally across all requests. By orchestrating the token-level parallelism, Flover exhibits optimal hardware efficiency and significantly spares the system resources. By further employing a fast buffer reordering algorithm that allows memory eviction of finished tasks, it brings over 11x inference speedup on GPT and 16x on LLAMA compared to the cutting-edge solutions provided by NVIDIA FasterTransformer. Crucially, by leveraging the advanced tensor parallel technique, Flover proves efficacious across diverse computational landscapes, from single-GPU setups to distributed scenarios, thereby offering robust performance optimization that adapts to variable use cases.

Large language models (LLMs) have revolutionized the field of AI, demonstrating unprecedented capacity across various tasks. However, the inference process for LLMs comes with significant computational costs. In this paper, we propose an efficient LLM inference pipeline that harnesses the power of LLMs. Our approach begins by tapping into the potential of LLMs to accurately perceive and predict the response length with minimal overhead. By leveraging this information, we introduce an efficient sequence scheduling technique that groups queries with similar response lengths into micro-batches. We evaluate our approach on real-world instruction datasets using the LLaMA-based model, and our results demonstrate an impressive 86% improvement in inference throughput without compromising effectiveness. Notably, our method is orthogonal to other inference acceleration techniques, making it a valuable addition to many existing toolkits (e.g., FlashAttention, Quantization) for LLM inference.

Sparse Mixture of Experts (MoE) models, while outperforming dense Large Language Models (LLMs) in terms of performance, face significant deployment challenges during inference due to their high memory demands. Existing offloading techniques, which involve swapping activated and idle experts between the GPU and CPU, often suffer from rigid expert caching mechanisms. These mechanisms fail to adapt to dynamic routing, leading to inefficient cache utilization, or incur prohibitive costs for prediction training. To tackle these inference-specific challenges, we introduce ExpertFlow, a comprehensive system specifically designed to enhance inference efficiency by accommodating flexible routing and enabling efficient expert scheduling between CPU and GPU. This reduces overhead and boosts system performance. Central to our approach is a predictive routing path-based offloading mechanism that utilizes a lightweight predictor to accurately forecast routing paths before computation begins. This proactive strategy allows for real-time error correction in expert caching, significantly increasing cache hit ratios and reducing the frequency of expert transfers, thereby minimizing I/O overhead. Additionally, we implement a dynamic token scheduling strategy that optimizes MoE inference by rearranging input tokens across different batches. This method not only reduces the number of activated experts per batch but also improves computational efficiency. Our extensive experiments demonstrate that ExpertFlow achieves up to 93.72\% GPU memory savings and enhances inference speed by 2 to 10 times compared to baseline methods, highlighting its effectiveness and utility as a robust solution for resource-constrained inference scenarios.

Long-form video question answering (VQA) overwhelms current vision-language models (VLMs) because attention and key-value (KV) caches grow with runtime, forcing either expensive inference or near-sighted sliding windows. We introduce CacheFlow, a training-free pipeline that pairs Dynamic Token Dropping (DTD) with a compressive long-term memory. DTD prunes per-patch tokens online via cosine similarity to the previous frame, and surviving tokens are packed into fixed-size blocks. This online, per-frame processing makes our approach fundamentally suited for live streaming VQA. As blocks are processed, each one's keys are summarized by a tiny recurrent encoder to form a retrieval index, while the block's full KV pairs are offloaded and later rehydrated for generation, preserving answer fidelity. At inference, a consensus-based retrieval mechanism retrieves only the Top-K most relevant blocks and attends over both the retrieved and local context for precise, long-range reasoning. CacheFlow is drop-in, architecture-agnostic, and requires no fine-tuning. Experiments on both offline and streaming VQA benchmarks demonstrate that CacheFlow outperforms current strong baselines, while processing up to 87% less tokens. Our dual approach enables VLMs to be both efficient and context-aware, paving the way for practical long-form video understanding.

Multimodal large language models (MLLMs) have made significant progress in visual-language reasoning, but their ability to efficiently handle long videos remains limited. Despite recent advances in long-context MLLMs, storing and attending to the key-value (KV) cache for long visual contexts incurs substantial memory and computational overhead. Existing visual compression methods require either encoding the entire visual context before compression or having access to the questions in advance, which is impractical for long video understanding and multi-turn conversational settings. In this work, we propose StreamMem, a query-agnostic KV cache memory mechanism for streaming video understanding. Specifically, StreamMem encodes new video frames in a streaming manner, compressing the KV cache using attention scores between visual tokens and generic query tokens, while maintaining a fixed-size KV memory to enable efficient question answering (QA) in memory-constrained, long-video scenarios. Evaluation on three long video understanding and two streaming video question answering benchmarks shows that StreamMem achieves state-of-the-art performance in query-agnostic KV cache compression and is competitive with query-aware compression approaches.

Recent advances have demonstrated the potential of decoderonly large language models (LLMs) for automatic speech recognition (ASR). However, enabling streaming recognition within this framework remains a challenge. In this work, we propose a novel streaming ASR approach that integrates a read/write policy network with monotonic chunkwise attention (MoChA) to dynamically segment speech embeddings. These segments are interleaved with label sequences during training, enabling seamless integration with the LLM. During inference, the audio stream is buffered until the MoChA module triggers a read signal, at which point the buffered segment together with the previous token is fed into the LLM for the next token prediction. We also introduce a minimal-latency training objective to guide the policy network toward accurate segmentation boundaries. Furthermore, we adopt a joint training strategy in which a non-streaming LLM-ASR model and our streaming model share parameters. Experiments on the AISHELL-1 and AISHELL-2 Mandarin benchmarks demonstrate that our method consistently outperforms recent streaming ASR baselines, achieving character error rates of 5.1% and 5.5%, respectively. The latency optimization results in a 62.5% reduction in average token generation delay with negligible impact on recognition accuracy

Retrieval-Augmented Generation (RAG) systems critically depend on effective document chunking strategies to balance retrieval quality, latency, and operational cost. Traditional chunking approaches, such as fixed-size, rule-based, or fully agentic chunking, often suffer from high token consumption, redundant text generation, limited scalability, and poor debuggability, especially for large-scale web content ingestion. In this paper, we propose Web Retrieval-Aware Chunking (W-RAC), a novel, cost-efficient chunking framework designed specifically for web-based documents. W-RAC decouples text extraction from semantic chunk planning by representing parsed web content as structured, ID-addressable units and leveraging large language models (LLMs) only for retrieval-aware grouping decisions rather than text generation. This significantly reduces token usage, eliminates hallucination risks, and improves system observability.Experimental analysis and architectural comparison demonstrate that W-RAC achieves comparable or better retrieval performance than traditional chunking approaches while reducing chunking-related LLM costs by an order of magnitude.

Models for low-latency, streaming applications could benefit from the knowledge capacity of larger models, but edge devices cannot run these models due to resource constraints. A possible solution is to transfer hints during inference from a large model running remotely to a small model running on-device. However, this incurs a communication delay that breaks real-time requirements and does not guarantee that both models will operate on the same data at the same time. We propose knowledge boosting, a novel technique that allows a large model to operate on time-delayed input during inference, while still boosting small model performance. Using a streaming neural network that processes 8 ms chunks, we evaluate different speech separation and enhancement tasks with communication delays of up to six chunks or 48 ms. Our results show larger gains where the performance gap between the small and large models is wide, demonstrating a promising method for large-small model collaboration for low-latency applications. Code, dataset, and audio samples available at https://knowledgeboosting.cs.washington.edu/.

Modern language models still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level of granularity, which often leads to brittle and counterintuitive behaviors even in otherwise strong reasoning models. We introduce ByteFlow Net, a new hierarchical architecture that removes tokenizers entirely and instead enables models to learn their own segmentation of raw byte streams into semantically meaningful units. ByteFlow Net performs compression-driven segmentation based on the coding rate of latent representations, yielding adaptive boundaries while preserving a static computation graph via Top-K selection. Unlike prior self-tokenizing methods that depend on brittle heuristics with human-designed inductive biases, ByteFlow Net adapts its internal representation granularity to the input itself. Experiments demonstrate that this compression-based chunking strategy yields substantial performance gains, with ByteFlow Net outperforming both BPE-based Transformers and previous byte-level architectures. These results suggest that end-to-end, tokenizer-free modeling is not only feasible but also more effective, opening a path toward more adaptive and information-grounded language models.

Despite advancements in Video Large Language Models (Vid-LLMs) improving multimodal understanding, challenges persist in streaming video reasoning due to its reliance on contextual information. Existing paradigms feed all available historical contextual information into Vid-LLMs, resulting in a significant computational burden for visual data processing. Furthermore, the inclusion of irrelevant context distracts models from key details. This paper introduces a challenging task called Context-guided Streaming Video Reasoning (CogStream), which simulates real-world streaming video scenarios, requiring models to identify the most relevant historical contextual information to deduce answers for questions about the current stream. To support CogStream, we present a densely annotated dataset featuring extensive and hierarchical question-answer pairs, generated by a semi-automatic pipeline. Additionally, we present CogReasoner as a baseline model. It effectively tackles this task by leveraging visual stream compression and historical dialogue retrieval. Extensive experiments prove the effectiveness of this method.

Distributed inference of large language models (LLMs) can introduce overheads of up to 20% even over GPUs connected via high-speed interconnects such as NVLINK. Multiple techniques have been proposed to mitigate these overheads by decomposing computations into finer-grained tasks and overlapping communication with sub-tasks as they complete. However, fine-grained decomposition of a large computation into many smaller computations on GPUs results in overheads. Further, the communication itself uses many streaming multiprocessors (SMs), adding to the overhead. We present TokenWeave to address these challenges. TokenWeave proposes a Token-Splitting technique that divides the tokens in the inference batch into two approximately equal subsets in a wave-aware manner. The computation of one subset is then overlapped with the communication of the other. In addition, TokenWeave optimizes the order of the layer normalization computation with respect to communication operations and implements a novel fused AllReduce-RMSNorm kernel carefully leveraging Multimem instruction support available on NVIDIA Hopper GPUs. These optimizations allow TokenWeave to perform communication and RMSNorm using only 2-8 SMs. Moreover, our kernel enables the memory bound RMSNorm to be overlapped with the other batch's computation, providing additional gains. Our evaluations demonstrate up to 29% latency gains and up to 26% throughput gains across multiple models and workloads. In several settings, TokenWeave results in better performance compared to an equivalent model with all communication removed.

Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we decompose the inference process into the encoding, denoising, and decoding stages, and observe that cache-based acceleration methods often lead to substantial memory surges in the latter two stages. To address this problem, we analyze the characteristics of inference across different stages and propose stage-specific strategies for reducing memory consumption: 1) Asynchronous Cache Swapping. 2) Feature chunk. 3) Slicing latents to decode. At the same time, we ensure that the time overhead introduced by these three strategies remains lower than the acceleration gains themselves. Compared with the baseline, our approach achieves faster inference speed and lower memory usage, while maintaining quality degradation within an acceptable range. The Code is available at https://github.com/NKUShaw/LightCache .

To reduce memory costs in long-context inference with Large Language Models (LLMs), many recent works focus on compressing the key-value (KV) cache of different tokens. However, we identify that the previous KV cache compression methods measure token importance individually, neglecting the dependency between different tokens in the real-world language characterics. In light of this, we introduce ChunkKV, grouping the tokens in a chunk as a basic compressing unit, and retaining the most informative semantic chunks while discarding the less important ones. Furthermore, observing that ChunkKV exhibits higher similarity in the preserved indices across different layers, we propose layer-wise index reuse to further reduce computational overhead. We evaluated ChunkKV on cutting-edge long-context benchmarks including LongBench and Needle-In-A-HayStack, as well as the GSM8K and JailbreakV in-context learning benchmark. Our experiments with instruction tuning and multi-step reasoning (O1 and R1) LLMs, achieve up to 10\% performance improvement under aggressive compression ratios compared to existing methods.

Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works demonstrating 20-80% parameter reductions at minimal accuracy loss. Previous SVD-based approaches have focused primarily on reducing the memory footprint of model weights, largely overlooking the additional activation memory overhead incurred during inference when applying truncated factors via standard dense CUDA kernels. Our experiments demonstrate that this activation overhead, scaling with sequence length and hidden dimension, prevents current SVD compression techniques from achieving any reduction in peak inference memory, thereby limiting their viability for real-world, on-device deployments. We introduce FlashSVD, a novel, end-to-end rank-aware streaming inference framework specifically designed for SVD-compressed large language models. FlashSVD can be seamlessly integrated with any model that employs SVD-based methods for parameter reduction. By fusing low-rank projection kernels directly into both the self-attention and feed-forward network (FFN) pipelines, FlashSVD avoid materializing full-size activation buffers. Instead, small tiles of the truncated factors are loaded into on-chip SRAM, multiplied and reduced on the fly, and immediately evicted, preserving high GPU occupancy and adding no extra latency. On standard encoder benchmarks (e.g., BERT-Base), FlashSVD cuts peak activation memory by up to 70.2% and intermediate transient memory by 75%, all while incur no accuracy loss with upstreaming compression methods, offering a practical path toward memory-constrained deployment of low-rank LLMs.

Multimodal large language models (MLLMs) have shown strong performance on offline video understanding, but most are limited to offline inference or have weak online reasoning, making multi-turn interaction over continuously arriving video streams difficult. Existing streaming methods typically use an interleaved perception-generation paradigm, which prevents concurrent perception and generation and leads to early memory decay as streams grow, hurting long-range dependency modeling. We propose Think While Watching, a memory-anchored streaming video reasoning framework that preserves continuous segment-level memory during multi-turn interaction. We build a three-stage, multi-round chain-of-thought dataset and adopt a stage-matched training strategy, while enforcing strict causality through a segment-level streaming causal mask and streaming positional encoding. During inference, we introduce an efficient pipeline that overlaps watching and thinking and adaptively selects the best attention backend. Under both single-round and multi-round streaming input protocols, our method achieves strong results. Built on Qwen3-VL, it improves single-round accuracy by 2.6% on StreamingBench and by 3.79% on OVO-Bench. In the multi-round setting, it maintains performance while reducing output tokens by 56%. Code is available at: https://github.com/wl666hhh/Think_While_Watching/

Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and spawning a new research direction. Their application in real-time communication is, however, still lagging behind due to their computation-heavy nature involving multiple calls of large DNNs. Here, we present Stream.FM, a frame-causal flow-based generative model with an algorithmic latency of 32 milliseconds (ms) and a total latency of 48 ms, paving the way for generative speech processing in real-time communication. We propose a buffered streaming inference scheme and an optimized DNN architecture, show how learned few-step numerical solvers can boost output quality at a fixed compute budget, explore model weight compression to find favorable points along a compute/quality tradeoff, and contribute a model variant with 24 ms total latency for the speech enhancement task. Our work looks beyond theoretical latencies, showing that high-quality streaming generative speech processing can be realized on consumer GPUs available today. Stream.FM can solve a variety of speech processing tasks in a streaming fashion: speech enhancement, dereverberation, codec post-filtering, bandwidth extension, STFT phase retrieval, and Mel vocoding. As we verify through comprehensive evaluations and a MUSHRA listening test, Stream.FM establishes a state-of-the-art for generative streaming speech restoration, exhibits only a reasonable reduction in quality compared to a non-streaming variant, and outperforms our recent work (Diffusion Buffer) on generative streaming speech enhancement while operating at a lower latency.

Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a series of methods based on block selection and compression to alleviate this problem, but they either have issues with semantic incompleteness or poor training-inference efficiency. To comprehensively address these challenges, we propose ChunkLLM, a lightweight and pluggable training framework. Specifically, we introduce two components: QK Adapter (Q-Adapter and K-Adapter) and Chunk Adapter. The former is attached to each Transformer layer, serving dual purposes of feature compression and chunk attention acquisition. The latter operates at the bottommost layer of the model, functioning to detect chunk boundaries by leveraging contextual semantic information. During the training phase, the parameters of the backbone remain frozen, with only the QK Adapter and Chunk Adapter undergoing training. Notably, we design an attention distillation method for training the QK Adapter, which enhances the recall rate of key chunks. During the inference phase, chunk selection is triggered exclusively when the current token is detected as a chunk boundary, thereby accelerating model inference. Experimental evaluations are conducted on a diverse set of long-text and short-text benchmark datasets spanning multiple tasks. ChunkLLM not only attains comparable performance on short-text benchmarks but also maintains 98.64% of the performance on long-context benchmarks while preserving a 48.58% key-value cache retention rate. Particularly, ChunkLLM attains a maximum speedup of 4.48x in comparison to the vanilla Transformer in the processing of 120K long texts.

Many use cases require retrieving smaller portions of text, and dense vector-based retrieval systems often perform better with shorter text segments, as the semantics are less likely to be "over-compressed" in the embeddings. Consequently, practitioners often split text documents into smaller chunks and encode them separately. However, chunk embeddings created in this way can lose contextual information from surrounding chunks, resulting in suboptimal representations. In this paper, we introduce a novel method called "late chunking," which leverages long context embedding models to first embed all tokens of the long text, with chunking applied after the transformer model and just before mean pooling. The resulting chunk embeddings capture the full contextual information, leading to superior results across various retrieval tasks without the need for additional training. Moreover, our method is generic enough to be applied to any long-context embedding model.

This paper presents MoE-Gen, a high-throughput MoE inference system optimized for single-GPU execution. Existing inference systems rely on model-based or continuous batching strategies, originally designed for interactive inference, which result in excessively small batches for MoE's key modules-attention and expert modules-leading to poor throughput. To address this, we introduce module-based batching, which accumulates tokens in host memory and dynamically launches large batches on GPUs to maximize utilization. Additionally, we optimize the choice of batch sizes for each module in an MoE to fully overlap GPU computation and communication, maximizing throughput. Evaluation demonstrates that MoE-Gen achieves 8-31x higher throughput compared to state-of-the-art systems employing model-based batching (FlexGen, MoE-Lightning, DeepSpeed), and offers even greater throughput improvements over continuous batching systems (e.g., vLLM and Ollama) on popular MoE models (DeepSeek and Mixtral) across offline inference tasks. MoE-Gen's source code is publicly available at https://github.com/EfficientMoE/MoE-Gen

Reconstructing 3D geometry from streaming video requires continuous inference under bounded resources. Recent geometric foundation models achieve impressive reconstruction quality through all-to-all attention, yet their quadratic cost confines them to short, offline sequences. Causal-attention variants such as StreamVGGT enable single-pass streaming but accumulate an ever-growing KV cache, exhausting GPU memory within hundreds of frames and precluding the long-horizon deployment that motivates streaming inference in the first place. We present OVGGT, a training-free framework that bounds both memory and compute to a fixed budget regardless of sequence length. Our approach combines Self-Selective Caching, which leverages FFN residual magnitudes to compress the KV cache while remaining fully compatible with FlashAttention, with Dynamic Anchor Protection, which shields coordinate-critical tokens from eviction to suppress geometric drift over extended trajectories. Extensive experiments on indoor, outdoor, and ultra-long sequence benchmarks demonstrate that OVGGT processes arbitrarily long videos within a constant VRAM envelope while achieving state-of-the-art 3D geometric accuracy.

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant improvement in offline video understanding. However, extending these capabilities to streaming video inputs, remains challenging, as existing models struggle to simultaneously maintain stable understanding performance, real-time responses, and low GPU memory overhead. To address this challenge, we propose HERMES, a novel training-free architecture for real-time and accurate understanding of video streams. Based on a mechanistic attention investigation, we conceptualize KV cache as a hierarchical memory framework that encapsulates video information across multiple granularities. During inference, HERMES reuses a compact KV cache, enabling efficient streaming understanding under resource constraints. Notably, HERMES requires no auxiliary computations upon the arrival of user queries, thereby guaranteeing real-time responses for continuous video stream interactions, which achieves 10times faster TTFT compared to prior SOTA. Even when reducing video tokens by up to 68% compared with uniform sampling, HERMES achieves superior or comparable accuracy across all benchmarks, with up to 11.4% gains on streaming datasets.

Recent streaming video understanding methods increasingly rely on complex memory mechanisms to handle long video streams. We challenge this trend with a simple finding: a sliding-window baseline that feeds only the most recent N frames to an off-the-shelf VLM already matches or surpasses published streaming models. We formalize this baseline as SimpleStream and evaluate it against 13 major offline and online video LLM baselines on OVO-Bench and StreamingBench. Despite its simplicity, SimpleStream delivers consistently strong performance. With only 4 recent frames, it reaches 67.7% average accuracy on OVO-Bench and 80.59% on StreamingBench. Controlled ablations further show that the value of longer context is backbone-dependent rather than uniformly increasing with model scale, and reveal a consistent perception-memory trade-off: adding more historical context can improve recall, but often weakens real-time perception. This suggests that stronger memory, retrieval, or compression modules should not be taken as evidence of progress unless they clearly outperform SimpleStream under the same protocol. We therefore argue that future streaming benchmarks should separate recent-scene perception from long-range memory, so that performance improvements from added complexity can be evaluated more clearly.

Inference of Large Language Models (LLMs) across computer clusters has become a focal point of research in recent times, with many acceleration techniques taking inspiration from CPU speculative execution. These techniques reduce bottlenecks associated with memory bandwidth, but also increase end-to-end latency per inference run, requiring high speculation acceptance rates to improve performance. Combined with a variable rate of acceptance across tasks, speculative inference techniques can result in reduced performance. Additionally, pipeline-parallel designs require many user requests to maintain maximum utilization. As a remedy, we propose PipeInfer, a pipelined speculative acceleration technique to reduce inter-token latency and improve system utilization for single-request scenarios while also improving tolerance to low speculation acceptance rates and low-bandwidth interconnects. PipeInfer exhibits up to a 2.15times improvement in generation speed over standard speculative inference. PipeInfer achieves its improvement through Continuous Asynchronous Speculation and Early Inference Cancellation, the former improving latency and generation speed by running single-token inference simultaneously with several speculative runs, while the latter improves speed and latency by skipping the computation of invalidated runs, even in the middle of inference.

Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video generation (typically 16 or 24 frames), ending up with hard-cuts when naively extended to the case of long video synthesis. To overcome these limitations, we introduce StreamingT2V, an autoregressive approach for long video generation of 80, 240, 600, 1200 or more frames with smooth transitions. The key components are:(i) a short-term memory block called conditional attention module (CAM), which conditions the current generation on the features extracted from the previous chunk via an attentional mechanism, leading to consistent chunk transitions, (ii) a long-term memory block called appearance preservation module, which extracts high-level scene and object features from the first video chunk to prevent the model from forgetting the initial scene, and (iii) a randomized blending approach that enables to apply a video enhancer autoregressively for infinitely long videos without inconsistencies between chunks. Experiments show that StreamingT2V generates high motion amount. In contrast, all competing image-to-video methods are prone to video stagnation when applied naively in an autoregressive manner. Thus, we propose with StreamingT2V a high-quality seamless text-to-long video generator that outperforms competitors with consistency and motion. Our code will be available at: https://github.com/Picsart-AI-Research/StreamingT2V

This paper presents StreamChat, a novel approach that enhances the interaction capabilities of Large Multimodal Models (LMMs) with streaming video content. In streaming interaction scenarios, existing methods rely solely on visual information available at the moment a question is posed, resulting in significant delays as the model remains unaware of subsequent changes in the streaming video. StreamChat addresses this limitation by innovatively updating the visual context at each decoding step, ensuring that the model utilizes up-to-date video content throughout the decoding process. Additionally, we introduce a flexible and efficient crossattention-based architecture to process dynamic streaming inputs while maintaining inference efficiency for streaming interactions. Furthermore, we construct a new dense instruction dataset to facilitate the training of streaming interaction models, complemented by a parallel 3D-RoPE mechanism that encodes the relative temporal information of visual and text tokens. Experimental results demonstrate that StreamChat achieves competitive performance on established image and video benchmarks and exhibits superior capabilities in streaming interaction scenarios compared to state-of-the-art video LMM.

Large Language Models (LLMs) have exhibited exceptional performance across a spectrum of natural language processing tasks. However, their substantial sizes pose considerable challenges, particularly in computational demands and inference speed, due to their quadratic complexity. In this work, we have identified a key pattern: certain seemingly meaningless special tokens (i.e., separators) contribute disproportionately to attention scores compared to semantically meaningful tokens. This observation suggests that information of the segments between these separator tokens can be effectively condensed into the separator tokens themselves without significant information loss. Guided by this insight, we introduce SepLLM, a plug-and-play framework that accelerates inference by compressing these segments and eliminating redundant tokens. Additionally, we implement efficient kernels for training acceleration. Experimental results across training-free, training-from-scratch, and post-training settings demonstrate SepLLM's effectiveness. Notably, using the Llama-3-8B backbone, SepLLM achieves over 50% reduction in KV cache on the GSM8K-CoT benchmark while maintaining comparable performance. Furthermore, in streaming settings, SepLLM effectively processes sequences of up to 4 million tokens or more while maintaining consistent language modeling capabilities.

Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks. The tree-search-based reasoning methods address this by surpassing the capabilities of chain-of-thought prompting, encouraging exploration of intermediate steps. However, such methods introduce significant inference latency due to the systematic exploration and evaluation of multiple thought paths. This paper introduces SeeD, a novel and efficient inference framework to optimize runtime speed and GPU memory management concurrently. By employing a scheduled speculative execution, SeeD efficiently handles multiple iterations for the thought generation and the state evaluation, leveraging a rounds-scheduled strategy to manage draft model dispatching. Extensive experimental evaluations on three reasoning datasets demonstrate superior speedup performance of SeeD, providing a viable path for batched inference in training-free speculative decoding.

We present Streamo, a real-time streaming video LLM that serves as a general-purpose interactive assistant. Unlike existing online video models that focus narrowly on question answering or captioning, Streamo performs a broad spectrum of streaming video tasks, including real-time narration, action understanding, event captioning, temporal event grounding, and time-sensitive question answering. To develop such versatility, we construct Streamo-Instruct-465K, a large-scale instruction-following dataset tailored for streaming video understanding. The dataset covers diverse temporal contexts and multi-task supervision, enabling unified training across heterogeneous streaming tasks. After training end-to-end on the instruction-following dataset through a streamlined pipeline, Streamo exhibits strong temporal reasoning, responsive interaction, and broad generalization across a variety of streaming benchmarks. Extensive experiments show that Streamo bridges the gap between offline video perception models and real-time multimodal assistants, making a step toward unified, intelligent video understanding in continuous video streams.

We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models. It addresses two fundamental challenges in adapting existing models into online scenarios: (1) limited capability for multi-turn real-time understanding, and (2) lack of proactive response mechanisms. Specifically, StreamBridge incorporates (1) a memory buffer combined with a round-decayed compression strategy, supporting long-context multi-turn interactions, and (2) a decoupled, lightweight activation model that can be effortlessly integrated into existing Video-LLMs, enabling continuous proactive responses. To further support StreamBridge, we construct Stream-IT, a large-scale dataset tailored for streaming video understanding, featuring interleaved video-text sequences and diverse instruction formats. Extensive experiments show that StreamBridge significantly improves the streaming understanding capabilities of offline Video-LLMs across various tasks, outperforming even proprietary models such as GPT-4o and Gemini 1.5 Pro. Simultaneously, it achieves competitive or superior performance on standard video understanding benchmarks.

Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low arithmetic intensity of small-batch inference by improving upon previous work in speculative decoding. First, we restructure the speculative batch as a tree, which reduces generation costs and increases the expected tokens per batch. Second, we add a second stage of speculative decoding. Taken together, we reduce single-batch decoding latency by 3.16x with a 762M parameter GPT-2-L model while perfectly preserving output quality.

A recent trend in LLMs is developing recurrent sub-quadratic models that improve long-context processing efficiency. We investigate leading large long-context models, focusing on how their fixed-size recurrent memory affects their performance. Our experiments reveal that, even when these models are trained for extended contexts, their use of long contexts remains underutilized. Specifically, we demonstrate that a chunk-based inference procedure, which identifies and processes only the most relevant portion of the input can mitigate recurrent memory failures and be effective for many long-context tasks: On LongBench, our method improves the overall performance of Falcon3-Mamba-Inst-7B by 14%, Falcon-Mamba-Inst-7B by 28%, RecurrentGemma-IT-9B by 50%, and RWKV6-Finch-7B by 51%. Surprisingly, this simple approach also leads to state-of-the-art results in the challenging LongBench v2 benchmark, showing competitive performance with equivalent size Transformers. Furthermore, our findings raise questions about whether recurrent models genuinely exploit long-range dependencies, as our single-chunk strategy delivers stronger performance - even in tasks that presumably require cross-context relations.

Diffusion language models (DLMs) generate text through iterative denoising, but inference requires full-sequence attention at every iteration, resulting in substantial redundant computation on masked tokens. Block-wise diffusion can reduce this cost, yet it typically relies on retraining and constrained update orders, limiting its direct applicability to pretrained DLMs. Our token-level analysis reveals pronounced structural locality in DLM inference. Decoding is driven by a small set of prefix-localized active tokens; the influence of distant undecoded context diminishes rapidly, and decoded tokens exhibit stage-wise temporal stability, enabling reuse of intermediate representations except for a brief post-decode transient. Motivated by these observations, we propose \placeholderThe source code is available at https://github.com/vhicrgit/Window-Diffusion., a window-based token pruning and caching method for inference. We maintain a local computation window that slides rightward as denoising progresses, and partition undecoded tokens into: (i) active tokens that are computed online, (ii) buffer tokens whose KV states are cached and periodically refreshed, and (iii) far-field tokens that are pruned outside the window. Computation is restricted to active and buffer tokens within the window, while far-field tokens are omitted at each stage. Experiments on LLaDA and Dream show that, under matched compute budgets, our method achieves up to 99times inference speedup while largely preserving generation performance.

To break the context limits of large language models (LLMs) that bottleneck reasoning accuracy and efficiency, we propose the Thread Inference Model (TIM), a family of LLMs trained for recursive and decompositional problem solving, and TIMRUN, an inference runtime enabling long-horizon structured reasoning beyond context limits. Together, TIM hosted on TIMRUN supports virtually unlimited working memory and multi-hop tool calls within a single language model inference, overcoming output limits, positional-embedding constraints, and GPU-memory bottlenecks. Performance is achieved by modeling natural language as reasoning trees measured by both length and depth instead of linear sequences. The reasoning trees consist of tasks with thoughts, recursive subtasks, and conclusions based on the concept we proposed in Schroeder et al, 2025. During generation, we maintain a working memory that retains only the key-value states of the most relevant context tokens, selected by a rule-based subtask-pruning mechanism, enabling reuse of positional embeddings and GPU memory pages throughout reasoning. Experimental results show that our system sustains high inference throughput, even when manipulating up to 90% of the KV cache in GPU memory. It also delivers accurate reasoning on mathematical tasks and handles information retrieval challenges that require long-horizon reasoning and multi-hop tool use.

End-to-end speech summarization has been shown to improve performance over cascade baselines. However, such models are difficult to train on very large inputs (dozens of minutes or hours) owing to compute restrictions and are hence trained with truncated model inputs. Truncation leads to poorer models, and a solution to this problem rests in block-wise modeling, i.e., processing a portion of the input frames at a time. In this paper, we develop a method that allows one to train summarization models on very long sequences in an incremental manner. Speech summarization is realized as a streaming process, where hypothesis summaries are updated every block based on new acoustic information. We devise and test strategies to pass semantic context across the blocks. Experiments on the How2 dataset demonstrate that the proposed block-wise training method improves by 3 points absolute on ROUGE-L over a truncated input baseline.

The size and compute characteristics of modern large language models have led to an increased interest in developing specialized kernels tailored for training and inference. Existing kernels primarily optimize for compute utilization, targeting the large-batch training and inference settings. However, low-batch inference, where memory bandwidth and kernel launch overheads contribute are significant factors, remains important for many applications of interest such as in edge deployment and latency-sensitive applications. This paper describes FlashFormer, a proof-of-concept kernel for accelerating single-batch inference for transformer-based large language models. Across various model sizes and quantizations settings, we observe nontrivial speedups compared to existing state-of-the-art inference kernels.

Deploying modern Speech Language Models (SpeechLMs) in streaming settings requires systems that provide low latency, high throughput, and strong guarantees of streamability. Existing systems fall short of supporting diverse models flexibly and efficiently. We present VoxServe, a unified serving system for SpeechLMs that optimizes streaming performance. VoxServe introduces a model-execution abstraction that decouples model architecture from system-level optimizations, thereby enabling support for diverse SpeechLM architectures within a single framework. Building on this abstraction, VoxServe implements streaming-aware scheduling and an asynchronous inference pipeline to improve end-to-end efficiency. Evaluations across multiple modern SpeechLMs show that VoxServe achieves 10-20x higher throughput than existing implementations at comparable latency while maintaining high streaming viability. The code of VoxServe is available at https://github.com/vox-serve/vox-serve.

Despite the significant advancements of Large Vision-Language Models (LVLMs) on established benchmarks, there remains a notable gap in suitable evaluation regarding their applicability in the emerging domain of long-context streaming video understanding. Current benchmarks for video understanding typically emphasize isolated single-instance text inputs and fail to evaluate the capacity to sustain temporal reasoning throughout the entire duration of video streams. To address these limitations, we introduce SVBench, a pioneering benchmark with temporal multi-turn question-answering chains specifically designed to thoroughly assess the capabilities of streaming video understanding of current LVLMs. We design a semi-automated annotation pipeline to obtain 49,979 Question-Answer (QA) pairs of 1,353 streaming videos, which includes generating QA chains that represent a series of consecutive multi-turn dialogues over video segments and constructing temporal linkages between successive QA chains. Our experimental results, obtained from 14 models in dialogue and streaming evaluations, reveal that while the closed-source GPT-4o outperforms others, most open-source LVLMs struggle with long-context streaming video understanding. We also construct a StreamingChat model, which significantly outperforms open-source LVLMs on our SVBench and achieves comparable performance on diverse vision-language benchmarks. We expect SVBench to advance the research of streaming video understanding by providing a comprehensive and in-depth analysis of current LVLMs. Our benchmark and model can be accessed at https://yzy-bupt.github.io/SVBench.

We propose ReKV, a novel training-free approach that enables efficient streaming video question-answering (StreamingVQA), by seamlessly integrating with existing Video Large Language Models (Video-LLMs). Traditional VideoQA systems struggle with long videos, as they must process entire videos before responding to queries, and repeat this process for each new question. In contrast, our approach analyzes long videos in a streaming manner, allowing for prompt responses as soon as user queries are received. Building on a common Video-LLM, we first incorporate a sliding-window attention mechanism, ensuring that input frames attend to a limited number of preceding frames, thereby reducing computational overhead. To prevent information loss, we store processed video key-value caches (KV-Caches) in RAM and disk, reloading them into GPU memory as needed. Additionally, we introduce a retrieval method that leverages an external retriever or the parameters within Video-LLMs to retrieve only query-relevant KV-Caches, ensuring both efficiency and accuracy in question answering. ReKV enables the separation of video encoding and question-answering across different processes and GPUs, significantly enhancing the efficiency of StreamingVQA. Through comprehensive experimentation, we validate the efficacy and practicality of our approach, which significantly boosts efficiency and enhances applicability over existing VideoQA models.

Real-time streaming joint audio-video generation for character animation requires a generator to speak the requested transcript, maintain visual identity across chunks, and run within a strict playback budget. These requirements are difficult to satisfy simultaneously: chunk-wise autoregressive generation can accumulate transcript-audio misalignment and visual drift, while the few-step distillation needed for low latency often degrades spatial diversity and temporal quality. We present StreamChar, a streaming framework that separates long-horizon orchestration from short-window audio-video denoising. An LLM-based orchestrator uses the transcript and historical context to produce frame-aligned audio conditions, and a joint audio-video DiT performs local bidirectional denoising with reference and motion-frame conditioning. For efficient deployment, we use a two-stage distillation pipeline that first compresses the sampler and then fine-tunes the student under online chunk rollouts. A progress-aware pointer aligns partial transcripts with generated audio during rollout training, and a sink-chunk memory provides a persistent visual anchor for reducing long-horizon drift. Experiments on short-clip and long-horizon protocols show that StreamChar runs in real time on a single H100 GPU and provides a favorable system-level trade-off among transcript fidelity, audio-visual synchronization, visual quality, and streaming stability compared with recent joint and audio-driven baselines.

Large language models are increasingly applied to multi-document and long-form inputs, yet long-context inference remains memory- and noise-inefficient. Key-value (KV) caching scales linearly with context length, while external retrieval methods often return lexically similar but causally irrelevant passages. We present S3-Attention, a memory-first inference-time framework that treats long-context processing as attention-aligned endogenous retrieval. S3-Attention decodes transient key and query projections into top-k sparse feature identifiers using lightweight sparse autoencoders, and constructs a CPU-based inverted index mapping features to token positions or spans during a single streaming scan. This design allows the KV cache to be discarded entirely and bounds GPU memory usage by the scan chunk size. At generation time, feature co-activation is used to retrieve compact evidence spans, optionally fused with BM25 for exact lexical matching. Under a unified LongBench evaluation protocol with fixed prompting, decoding, and matched token budgets, S3-Hybrid closely matches full-context inference across multiple model families and improves robustness in several information-dense settings. We also report an engineering limitation of the current prototype, which incurs higher wall-clock latency than optimized full-KV baselines, motivating future kernel-level optimization.

Long-context inference for Large Language Models (LLMs) is heavily limited by high computational demands. While several existing methods optimize attention computation, they still process the full set of hidden states at each layer, limiting overall efficiency. In this work, we propose SlimInfer, an innovative framework that aims to accelerate inference by directly pruning less critical prompt tokens during the forward pass. Our key insight is an information diffusion phenomenon: As information from critical tokens propagates through layers, it becomes distributed across the entire sequence. This diffusion process suggests that LLMs can maintain their semantic integrity when excessive tokens, even including these critical ones, are pruned in hidden states. Motivated by this, SlimInfer introduces a dynamic fine-grained pruning mechanism that accurately removes redundant tokens of hidden state at intermediate layers. This layer-wise pruning naturally enables an asynchronous KV cache manager that prefetches required token blocks without complex predictors, reducing both memory usage and I/O costs. Extensive experiments show that SlimInfer can achieve up to 2.53times time-to-first-token (TTFT) speedup and 1.88times end-to-end latency reduction for LLaMA3.1-8B-Instruct on a single RTX 4090, without sacrificing performance on LongBench. Our code will be released upon acceptance.

Autoregressive (AR) generation is the standard decoding paradigm for Large Language Models (LLMs), but its token-by-token nature limits parallelism at inference time. Diffusion Language Models (DLLMs) offer parallel decoding by recovering multiple masked tokens per step; however, in practice they often fail to translate this parallelism into deployment speed gains over optimized AR engines (e.g., vLLM). A key reason is that many DLLMs rely on bidirectional attention, which breaks standard prefix KV caching and forces repeated contextualization, undermining efficiency. We propose WeDLM, a diffusion decoding framework built entirely on standard causal attention to make parallel generation prefix-cache friendly. The core idea is to let each masked position condition on all currently observed tokens while keeping a strict causal mask, achieved by Topological Reordering that moves observed tokens to the physical prefix while preserving their logical positions. Building on this property, we introduce a streaming decoding procedure that continuously commits confident tokens into a growing left-to-right prefix and maintains a fixed parallel workload, avoiding the stop-and-wait behavior common in block diffusion methods. Experiments show that WeDLM preserves the quality of strong AR backbones while delivering substantial speedups, approaching 3x on challenging reasoning benchmarks and up to 10x in low-entropy generation regimes; critically, our comparisons are against AR baselines served by vLLM under matched deployment settings, demonstrating that diffusion-style decoding can outperform an optimized AR engine in practice.

Speculative decoding accelerates LLM inference by using a draft model to look ahead, but gains are capped by the cost of autoregressive draft generation: increasing draft size elevates acceptance rates but introduces additional latency overhead exacerbating the speed-accuracy tradeoff. Prior methods (Medusa, Hydra, EAGLE) partially reduce draft cost but either degrade acceptance or introduce overheads that limit scaling. We present Mirror Speculative Decoding (Mirror-SD), an inference algorithm that breaks the latency-acceptance tradeoff. Mirror-SD launches branch-complete rollouts from early-exit signals in parallel with the target model's suffix and explicitly maps computation across heterogeneous accelerators (GPU and NPU) to exploit cross-device parallelism. The draft speculates forward continuations for the target to verify, while the target simultaneously speculates correction paths for the draft, converting speculation into two complementary execution pipelines. To further cut draft latency without weakening acceptance semantics, we add speculative streaming so the draft emits multiple tokens per step. This dual strategy of parallel heterogeneous execution plus multi-token speculative streaming pushes speculative decoding toward its ideal regime of high acceptance with low overhead. On SpecBench with server-scale models from 14B to 66B parameters, Mirror-SD delivers consistent end-to-end gains, achieving 2.8x-5.8x wall-time speedups across diverse tasks and a 30% average relative improvement over the strongest baseline, EAGLE3.

As large language models (LLMs) evolve to handle increasingly longer contexts, serving inference requests for context lengths in the range of millions of tokens presents unique challenges. While existing techniques are effective for training, they fail to address the unique challenges of inference, such as varying prefill and decode phases and their associated latency constraints - like Time to First Token (TTFT) and Time Between Tokens (TBT). Furthermore, there are no long context inference solutions that allow batching requests to increase the hardware utilization today. In this paper, we propose three key innovations for efficient interactive long context LLM inference, without resorting to any approximation: adaptive chunking to reduce prefill overheads in mixed batching, Sequence Pipeline Parallelism (SPP) to lower TTFT, and KV Cache Parallelism (KVP) to minimize TBT. These contributions are combined into a 3D parallelism strategy, enabling Mnemosyne to scale interactive inference to context lengths at least up to 10 million tokens with high throughput enabled with batching. To our knowledge, Mnemosyne is the first to be able to achieve support for 10 million long context inference efficiently, while satisfying production-grade SLOs on TBT (30ms) on contexts up to and including 10 million.

Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continuously constructing new and evicting old key-value(KV) caches is required for unbounded streams. Secondly, due to the high cost of collecting and training on unbounded streams, models must learn from short sequences while generalizing to long streams. Existing streaming VideoVLLMs fail to scale to unbounded video streams or focus on cache reuse strategies, leaving the impact of cache construction underexplored. In this paper, we propose Decoupled Streaming Cache(DSCache), a training-free cache construction mechanism that adapts pretrained offline models to streaming settings. DSCache maintains a cumulative past KV cache while constructing a separate instant cache on-demand, decoupled from past caches to preserve the informativeness of recent inputs. To enable position extrapolation beyond the training length, DSCache further incorporates a position-agnostic encoding strategy, ensuring KV caches to support unseen positions and preventing position overflow. Experiments on Streaming Video QA benchmarks demonstrate DSCache's state-of-the-art performance, with an average 2.5% accuracy gains over prior methods.

We propose TETRIS, a novel method that optimizes the total throughput of batch speculative decoding in multi-request settings. Unlike existing methods that optimize for a single request or a group of requests as a whole, TETRIS actively selects the most promising draft tokens (for every request in a batch) to be accepted when verified in parallel, resulting in fewer rejected tokens and hence less wasted computing resources. Such an effective resource utilization to achieve fast inference in large language models (LLMs) is especially important to service providers with limited inference capacity. Compared to baseline speculative decoding, TETRIS yields a consistently higher acceptance rate and more effective utilization of the limited inference capacity. We show theoretically and empirically that TETRIS outperforms baseline speculative decoding and existing methods that dynamically select draft tokens, leading to a more efficient batch inference in LLMs.

Large language models (LLMs) propel the prosperity of interactive AI applications showcased by ChatGPT that demand timely response of inference services. However, LLM inference is computation intensive and memory intensive, and improper parameter configuration at LLM platforms may exacerbate the inference time. In this paper, we analyze the impact of LLM output token distribution on the inference queueing delay, where the max-token clipping and the batched inference are considered. By formulating an M/G/1 model, we observe that enforcing a maximum output token limit on a very small fraction of inference requests can significantly reduce the queueing delay, and our model facilitates the selection of the optimal limit. For the batch inference, we model the service process as a bulk queue in which the batch processing time is affected by the batch size and the maximum token size inside this batch jointly. The queueing delays of the batching of all buffered requests (dynamic batching), the batching of constant number of requests (fixed batching), and the batching without intra-batch waiting (elastic batching) are derived. Experimental results show that our mathematical models coincide with the event-driven simulations well.

The rapid development of Multimodal Large Language Models (MLLMs) has expanded their capabilities from image comprehension to video understanding. However, most of these MLLMs focus primarily on offline video comprehension, necessitating extensive processing of all video frames before any queries can be made. This presents a significant gap compared to the human ability to watch, listen, think, and respond to streaming inputs in real time, highlighting the limitations of current MLLMs. In this paper, we introduce StreamingBench, the first comprehensive benchmark designed to evaluate the streaming video understanding capabilities of MLLMs. StreamingBench assesses three core aspects of streaming video understanding: (1) real-time visual understanding, (2) omni-source understanding, and (3) contextual understanding. The benchmark consists of 18 tasks, featuring 900 videos and 4,500 human-curated QA pairs. Each video features five questions presented at different time points to simulate a continuous streaming scenario. We conduct experiments on StreamingBench with 13 open-source and proprietary MLLMs and find that even the most advanced proprietary MLLMs like Gemini 1.5 Pro and GPT-4o perform significantly below human-level streaming video understanding capabilities. We hope our work can facilitate further advancements for MLLMs, empowering them to approach human-level video comprehension and interaction in more realistic scenarios.

Streaming visual transformers like StreamVGGT achieve strong 3D perception but suffer from unbounded growth of key value (KV) memory, which limits scalability. We propose a training-free, inference-time token eviction policy that bounds memory by discarding redundant tokens while keeping the most informative ones. Our method uses significantly less memory with little to no drop in accuracy: on 7-Scenes with long sequences it reduces peak memory from 18.63 GB to 9.39 GB while accuracy and completeness drop by only 0.003. Under strict memory budgets, eviction enables denser frame sampling, which improves reconstruction accuracy compared to the baseline. Experiments across video depth estimation (Sintel, KITTI), 3D reconstruction (7-Scenes, NRGBD), and camera pose estimation (Sintel, TUM-dynamics) show that our approach closely matches StreamVGGT at a fraction of the memory and makes long-horizon streaming inference more practical.

Linear attention has recently gained significant attention for long-context inference due to its constant decoding cost with respect to context length. However, existing serving systems typically serve linear attention by recurrently computing and updating a large linear attention state in every decoding step. Since the state is much larger than the per-token key and value, recurrent decoding incurs substantial memory access and becomes inefficient for serving linear attention. In this paper, we propose KVBuffer, an IO-aware serving mechanism for linear attention. By buffering recent keys and values, KVBuffer enables serving systems to compute linear attention outputs in more flexible and memory-efficient ways. For decoding, KVBuffer enables chunkwise computation, which reduces average memory access and decoding latency by deferring state updates and applying them in batch. For speculative decoding, KVBuffer verifies draft tokens in parallel and avoids storing temporary states. For short contexts, KVBuffer computes attention outputs directly from buffered keys and values, without creating or updating the linear attention state. We implement KVBuffer in SGLang for Qwen3-Next. Our evaluations show that KVBuffer can reduce linear attention decoding latency by up to 45.17% and increase the maximum number of serving requests by 5x for speculative decoding when verifying four draft tokens.

The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV) caching, which accelerates decoding but quickly exhausts GPU memory. In this paper, we introduce the first queueing-theoretic framework that explicitly incorporates both computation and GPU memory constraints into the analysis of LLM inference. Based on this framework, we derive rigorous stability and instability conditions that determine whether an LLM inference service can sustain incoming demand without unbounded queue growth. This result offers a powerful tool for system deployment, potentially addressing the core challenge of GPU provisioning. By combining an estimated request arrival rate with our derived stable service rate, operators can calculate the necessary cluster size to avoid both costly over-purchasing and performance-violating under-provisioning. We further validate our theoretical predictions through extensive experiments in real GPU production environments. Our results show that the predicted stability conditions are highly accurate, with deviations typically within 10%.

Accelerating inference in Large Language Models (LLMs) is critical for real-time interactions, as they have been widely incorporated into real-world services. Speculative decoding, a fully algorithmic solution, has gained attention for improving inference speed by drafting and verifying tokens, thereby generating multiple tokens in a single forward pass. However, current drafting strategies usually require significant fine-tuning or have inconsistent performance across tasks. To address these challenges, we propose Hierarchy Drafting (HD), a novel lossless drafting approach that organizes various token sources into multiple databases in a hierarchical framework based on temporal locality. In the drafting step, HD sequentially accesses multiple databases to obtain draft tokens from the highest to the lowest locality, ensuring consistent acceleration across diverse tasks and minimizing drafting latency. Our experiments on Spec-Bench using LLMs with 7B and 13B parameters demonstrate that HD outperforms existing database drafting methods, achieving robust inference speedups across model sizes, tasks, and temperatures.

The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (SSMs) provide scalable alternatives but are typically restricted to first-order or kernel-based approximations, which can limit expressivity. We introduce Higher-order Linear Attention (HLA), a causal, streaming mechanism that realizes higher interactions via compact prefix sufficient statistics. In the second-order case, HLA maintains a constant-size state and computes per-token outputs in linear time without materializing any n times n matrices. We give closed-form streaming identities, a strictly causal masked variant using two additional summaries, and a chunk-parallel training scheme based on associative scans that reproduces the activations of a serial recurrence exactly. We further outline extensions to third and higher orders. Collectively, these results position HLA as a principled, scalable building block that combines attention-like, data-dependent mixing with the efficiency of modern recurrent architectures. Project Page: https://github.com/yifanzhang-pro/HLA.

There is growing demand for performing inference with hundreds of thousands of input tokens on trained transformer models. Inference at this extreme scale demands significant computational resources, hindering the application of transformers at long contexts on commodity (i.e not data center scale) hardware. To address the inference time costs associated with running self-attention based transformer language models on long contexts and enable their adoption on widely available hardware, we propose a tunable mechanism that reduces the cost of the forward pass by attending to only the most relevant tokens at every generation step using a top-k selection mechanism. We showcase the efficiency gains afforded by our method by performing inference on context windows up to 1M tokens using approximately 16GB of GPU RAM. Our experiments reveal that models are capable of handling the sparsity induced by the reduced number of keys and values. By attending to less than 2% of input tokens, we achieve over 95% of model performance on common benchmarks (RULER, AlpacaEval, and Open LLM Leaderboard).

MoE (Mixture of Experts) prevails as a neural architecture that can scale modern transformer-based LLMs (Large Language Models) to unprecedented scales. Nevertheless, large MoEs' great demands of computing power, memory capacity and memory bandwidth make scalable serving a fundamental challenge and efficient parallel inference has become a requisite to attain adequate throughput under latency constraints. DeepSpeed-MoE, one state-of-the-art MoE inference framework, adopts a 3D-parallel paradigm including EP (Expert Parallelism), TP (Tensor Parallel) and DP (Data Parallelism). However, our analysis shows DeepSpeed-MoE's inference efficiency is largely bottlenecked by EP, which is implemented with costly all-to-all collectives to route token activation. Our work aims to boost DeepSpeed-MoE by strategically reducing EP's communication overhead with a technique named Speculative MoE. Speculative MoE has two speculative parallelization schemes, speculative token shuffling and speculative expert grouping, which predict outstanding tokens' expert routing paths and pre-schedule tokens and experts across devices to losslessly trim EP's communication volume. Besides DeepSpeed-MoE, we also build Speculative MoE into a prevailing MoE inference engine SGLang. Experiments show Speculative MoE can significantly boost state-of-the-art MoE inference frameworks on fast homogeneous and slow heterogeneous interconnects.

Large Language Models (LLMs) based on Mixture-of-Experts (MoE) architecture are showing promising performance on various tasks. However, running them on resource-constrained settings, where GPU memory resources are not abundant, is challenging due to huge model sizes. Existing systems that offload model weights to CPU memory suffer from the significant overhead of frequently moving data between CPU and GPU. In this paper, we propose Fiddler, a resource-efficient inference engine with CPU-GPU orchestration for MoE models. The key idea of Fiddler is to use the computation ability of the CPU to minimize the data movement between the CPU and GPU. Our evaluation shows that Fiddler can run the uncompressed Mixtral-8x7B model, which exceeds 90GB in parameters, to generate over 3 tokens per second on a single GPU with 24GB memory, showing an order of magnitude improvement over existing methods. The code of Fiddler is publicly available at https://github.com/efeslab/fiddler

Retrieval augmentation addresses many critical problems in large language models such as hallucination, staleness, and privacy leaks. However, running retrieval-augmented language models (LMs) is slow and difficult to scale due to processing large amounts of retrieved text. We introduce binary token representations (BTR), which use 1-bit vectors to precompute every token in passages, significantly reducing computation during inference. Despite the potential loss of accuracy, our new calibration techniques and training objectives restore performance. Combined with offline and runtime compression, this only requires 127GB of disk space for encoding 3 billion tokens in Wikipedia. Our experiments show that on five knowledge-intensive NLP tasks, BTR accelerates state-of-the-art inference by up to 4x and reduces storage by over 100x while maintaining over 95% task performance.

Large Language Models (LLMs) for Generative AI have achieved remarkable progress, evolving into sophisticated and versatile tools widely adopted across various domains and applications. However, the substantial memory overhead caused by their vast number of parameters, combined with the high computational demands of the attention mechanism, poses significant challenges in achieving low latency and high throughput for LLM inference services. Recent advancements, driven by groundbreaking research, have significantly accelerated progress in this field. This paper provides a comprehensive survey of these methods, covering fundamental instance-level approaches, in-depth cluster-level strategies, emerging scenario directions, and other miscellaneous but important areas. At the instance level, we review model placement, request scheduling, decoding length prediction, storage management, and the disaggregation paradigm. At the cluster level, we explore GPU cluster deployment, multi-instance load balancing, and cloud service solutions. For emerging scenarios, we organize the discussion around specific tasks, modules, and auxiliary methods. To ensure a holistic overview, we also highlight several niche yet critical areas. Finally, we outline potential research directions to further advance the field of LLM inference serving.

We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better understanding of the engineering tradeoffs for inference for large Transformer-based models is important as use cases of these models are growing rapidly throughout application areas. We develop a simple analytical model for inference efficiency to select the best multi-dimensional partitioning techniques optimized for TPU v4 slices based on the application requirements. We combine these with a suite of low-level optimizations to achieve a new Pareto frontier on the latency and model FLOPS utilization (MFU) tradeoffs on 500B+ parameter models that outperforms the FasterTransformer suite of benchmarks. We further show that with appropriate partitioning, the lower memory requirements of multiquery attention (i.e. multiple query heads share single key/value head) enables scaling up to 32x larger context lengths. Finally, we achieve a low-batch-size latency of 29ms per token during generation (using int8 weight quantization) and a 76% MFU during large-batch-size processing of input tokens, while supporting a long 2048-token context length on the PaLM 540B parameter model.

Understanding long videos with multimodal large language models (MLLMs) remains challenging due to the heavy redundancy across frames and the need for temporally coherent representations. Existing static strategies, such as sparse sampling, frame compression, and clustering, are optimized for offline settings and often produce fragmented or over-compressed outputs when applied to continuous video streams. We present VideoScaffold, a dynamic representation framework designed for streaming video understanding. It adaptively adjusts event granularity according to video duration while preserving fine-grained visual semantics. VideoScaffold introduces two key components: Elastic-Scale Event Segmentation (EES), which performs prediction-guided segmentation to dynamically refine event boundaries, and Hierarchical Event Consolidation (HEC), which progressively aggregates semantically related segments into multi-level abstractions. Working in concert, EES and HEC enable VideoScaffold to transition smoothly from fine-grained frame understanding to abstract event reasoning as the video stream unfolds. Extensive experiments across both offline and streaming video understanding benchmarks demonstrate that VideoScaffold achieves state-of-the-art performance. The framework is modular and plug-and-play, seamlessly extending existing image-based MLLMs to continuous video comprehension. The code is available at https://github.com/zheng980629/VideoScaffold.

We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an offline manner, where the model consumes the complete input sequence before generating the first output timestep. Alternatively, streaming sequence-to-sequence rely on learning a policy for choosing when to advance on the input stream, or write to the output stream. DSM instead models already time-aligned streams with a decoder-only language model. By moving the alignment to a pre-processing step,and introducing appropriate delays between streams, DSM provides streaming inference of arbitrary output sequences, from any input combination, making it applicable to many sequence-to-sequence problems. In particular, given text and audio streams, automatic speech recognition (ASR) corresponds to the text stream being delayed, while the opposite gives a text-to-speech (TTS) model. We perform extensive experiments for these two major sequence-to-sequence tasks, showing that DSM provides state-of-the-art performance and latency while supporting arbitrary long sequences, being even competitive with offline baselines. Code, samples and demos are available at https://github.com/kyutai-labs/delayed-streams-modeling

In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks directly from the given demonstrations without requiring gradient updates. While recent advances have expanded context windows to accommodate more demonstrations, this approach increases inference costs without necessarily improving performance. To mitigate these issues, We propose StreamAdapter, a novel approach that directly updates model parameters from context at test time, eliminating the need for explicit in-context demonstrations. StreamAdapter employs context mapping and weight absorption mechanisms to dynamically transform ICL demonstrations into parameter updates with minimal additional parameters. By reducing reliance on numerous in-context examples, StreamAdapter significantly reduce inference costs and allows for efficient inference with constant time complexity, regardless of demonstration count. Extensive experiments across diverse tasks and model architectures demonstrate that StreamAdapter achieves comparable or superior adaptation capability to ICL while requiring significantly fewer demonstrations. The superior task adaptation and context encoding capabilities of StreamAdapter on both language understanding and generation tasks provides a new perspective for adapting LLMs at test time using context, allowing for more efficient adaptation across scenarios and more cost-effective inference

Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding. In practice, block inference is crucial for avoiding order misalignment in global bidirectional decoding and improving output quality. However, the widely-used fixed, predefined block (naive) schedule is agnostic to semantic difficulty, making it a suboptimal strategy for both quality and efficiency: it can force premature commitments to uncertain positions while delaying easy positions near block boundaries. In this work, we analyze the limitations of naive block scheduling and disclose the importance of dynamically adapting the schedule to semantic difficulty for reliable and efficient inference. Motivated by this, we propose Dynamic Sliding Block (DSB), a training-free block scheduling method that uses a sliding block with a dynamic size to overcome the rigidity of the naive block. To further improve efficiency, we introduce DSB Cache, a training-free KV-cache mechanism tailored to DSB. Extensive experiments across multiple models and benchmarks demonstrate that DSB, together with DSB Cache, consistently improves both generation quality and inference efficiency for dLLMs. Code is released at https://github.com/lizhuo-luo/DSB.

Many LLM tasks are performed in large batches or even offline, and the performance indictor for which is throughput. These tasks usually show the characteristic of prefix sharing, where different prompt input can partially show the common prefix. However, the existing LLM inference engines tend to optimize the streaming requests and show limitations of supporting the large batched tasks with the prefix sharing characteristic. The existing solutions use the LRU-based cache to reuse the KV context of common prefix. The KV context that is about to be reused may prematurely be evicted with the implicit cache management. Even if not evicted, the lifetime of the shared KV context is extended since requests sharing the same context are not scheduled together, resulting in larger memory usage. These streaming oriented systems schedule the requests in the first-come-first-serve or similar order. As a result, the requests with larger ratio of decoding steps may be scheduled too late to be able to mix with the prefill chunks to increase the hardware utilization. Besides, the token and request number based batching can limit the size of token-batch, which keeps the GPU from saturating for the iterations dominated by decoding tokens. We propose BatchLLM to address the above problems. BatchLLM explicitly identifies the common prefixes globally. The requests sharing the same prefix will be scheduled together to reuse the KV context the best, which also shrinks the lifetime of common KV memory. BatchLLM reorders the requests and schedules the requests with larger ratio of decoding first to better mix the decoding tokens with the latter prefill chunks and applies memory-centric token batching to enlarge the token-batch sizes, which helps to increase the GPU utilization. Extensive evaluation shows that BatchLLM outperforms vLLM by 1.1x to 2x on a set of microbenchmarks and two typical industry workloads.

This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video (V2V) translation with user prompts. Unlike prior V2V methods using batches to process limited frames, we opt to process frames in a streaming fashion, to support unlimited frames. At the heart of StreamV2V lies a backward-looking principle that relates the present to the past. This is realized by maintaining a feature bank, which archives information from past frames. For incoming frames, StreamV2V extends self-attention to include banked keys and values and directly fuses similar past features into the output. The feature bank is continually updated by merging stored and new features, making it compact but informative. StreamV2V stands out for its adaptability and efficiency, seamlessly integrating with image diffusion models without fine-tuning. It can run 20 FPS on one A100 GPU, being 15x, 46x, 108x, and 158x faster than FlowVid, CoDeF, Rerender, and TokenFlow, respectively. Quantitative metrics and user studies confirm StreamV2V's exceptional ability to maintain temporal consistency.

Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present MotionStream, enabling sub-second latency with up to 29 FPS streaming generation on a single GPU. Our approach begins by augmenting a text-to-video model with motion control, which generates high-quality videos that adhere to the global text prompt and local motion guidance, but does not perform inference on the fly. As such, we distill this bidirectional teacher into a causal student through Self Forcing with Distribution Matching Distillation, enabling real-time streaming inference. Several key challenges arise when generating videos of long, potentially infinite time-horizons: (1) bridging the domain gap from training on finite length and extrapolating to infinite horizons, (2) sustaining high quality by preventing error accumulation, and (3) maintaining fast inference, without incurring growth in computational cost due to increasing context windows. A key to our approach is introducing carefully designed sliding-window causal attention, combined with attention sinks. By incorporating self-rollout with attention sinks and KV cache rolling during training, we properly simulate inference-time extrapolations with a fixed context window, enabling constant-speed generation of arbitrarily long videos. Our models achieve state-of-the-art results in motion following and video quality while being two orders of magnitude faster, uniquely enabling infinite-length streaming. With MotionStream, users can paint trajectories, control cameras, or transfer motion, and see results unfold in real-time, delivering a truly interactive experience.

Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any changes to the outputs, by computing several tokens in parallel. At the heart of our approach lie the observations that (1) hard language-modeling tasks often include easier subtasks that can be approximated well by more efficient models, and (2) using speculative execution and a novel sampling method, we can make exact decoding from the large models faster, by running them in parallel on the outputs of the approximation models, potentially generating several tokens concurrently, and without changing the distribution. Our method can accelerate existing off-the-shelf models without retraining or architecture changes. We demonstrate it on T5-XXL and show a 2X-3X acceleration compared to the standard T5X implementation, with identical outputs.

Language models are increasingly used to reason over content they were not trained on, such as new documents, evolving knowledge, and user-specific data. A common approach is retrieval-augmented generation (RAG), which stores verbatim documents externally (as chunks) and retrieves only a relevant subset at inference time for an LLM to reason over. However, this results in inefficient usage of test-time compute (LLM repeatedly reasons over the same documents); moreover, chunk retrieval can inject irrelevant context that increases unsupported generation. We propose a human-like non-parametric continual learning framework, where the base model remains fixed, and learning occurs by integrating each new experience into an external semantic memory state that accumulates and consolidates itself continually. We present Panini, which realizes this by representing documents as Generative Semantic Workspaces (GSW) -- an entity- and event-aware network of question-answer (QA) pairs, sufficient for an LLM to reconstruct the experienced situations and mine latent knowledge via reasoning-grounded inference chains on the network. Given a query, Panini only traverses the continually-updated GSW (not the verbatim documents or chunks), and retrieves the most likely inference chains. Across six QA benchmarks, Panini achieves the highest average performance, 5%-7% higher than other competitive baselines, while using 2-30x fewer answer-context tokens, supports fully open-source pipelines, and reduces unsupported answers on curated unanswerable queries. The results show that efficient and accurate structuring of experiences at write time -- as achieved by the GSW framework -- yields both efficiency and reliability gains at read time. Code is available at https://github.com/roychowdhuryresearch/gsw-memory.

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions to handle the computational demands. In this paper, we explore the utilization of CPUs for accelerating the inference of large language models. Specifically, we introduce a parallelized approach to enhance throughput by 1) Exploiting the parallel processing capabilities of modern CPU architectures, 2) Batching the inference request. Our evaluation shows the accelerated inference engine gives an 18-22x improvement in the generated token per sec. The improvement is more with longer sequence and larger models. In addition to this, we can also run multiple workers in the same machine with NUMA node isolation to further improvement in tokens/s. Table 2, we have received 4x additional improvement with 4 workers. This would also make Gen-AI based products and companies environment friendly, our estimates shows that CPU usage for Inference could reduce the power consumption of LLMs by 48.9% while providing production ready throughput and latency.

Retrievers, which form one of the most important recommendation stages, are responsible for efficiently selecting possible positive samples to the later stages under strict latency limitations. Because of this, large-scale systems always rely on approximate calculations and indexes to roughly shrink candidate scale, with a simple ranking model. Considering simple models lack the ability to produce precise predictions, most of the existing methods mainly focus on incorporating complicated ranking models. However, another fundamental problem of index effectiveness remains unresolved, which also bottlenecks complication. In this paper, we propose a novel index structure: streaming Vector Quantization model, as a new generation of retrieval paradigm. Streaming VQ attaches items with indexes in real time, granting it immediacy. Moreover, through meticulous verification of possible variants, it achieves additional benefits like index balancing and reparability, enabling it to support complicated ranking models as existing approaches. As a lightweight and implementation-friendly architecture, streaming VQ has been deployed and replaced all major retrievers in Douyin and Douyin Lite, resulting in remarkable user engagement gain.

Understanding continuous video streams plays a fundamental role in real-time applications including embodied AI and autonomous driving. Unlike offline video understanding, streaming video understanding requires the ability to process video streams frame by frame, preserve historical information, and make low-latency decisions. To address these challenges, our main contributions are three-fold. (i) We develop a novel streaming video backbone, termed as StreamFormer, by incorporating causal temporal attention into a pre-trained vision transformer. This enables efficient streaming video processing while maintaining image representation capability. (ii) To train StreamFormer, we propose to unify diverse spatial-temporal video understanding tasks within a multitask visual-language alignment framework. Hence, StreamFormer learns global semantics, temporal dynamics, and fine-grained spatial relationships simultaneously. (iii) We conduct extensive experiments on online action detection, online video instance segmentation, and video question answering. StreamFormer achieves competitive results while maintaining efficiency, demonstrating its potential for real-time applications.

Despite significant progress in Video Large Language Models (Video-LLMs) for offline video understanding, existing online Video-LLMs typically struggle to simultaneously process continuous frame-by-frame inputs and determine optimal response timing, often compromising real-time responsiveness and narrative coherence. To address these limitations, we introduce LiveStar, a pioneering live streaming assistant that achieves always-on proactive responses through adaptive streaming decoding. Specifically, LiveStar incorporates: (1) a training strategy enabling incremental video-language alignment for variable-length video streams, preserving temporal consistency across dynamically evolving frame sequences; (2) a response-silence decoding framework that determines optimal proactive response timing via a single forward pass verification; (3) memory-aware acceleration via peak-end memory compression for online inference on 10+ minute videos, combined with streaming key-value cache to achieve 1.53x faster inference. We also construct an OmniStar dataset, a comprehensive dataset for training and benchmarking that encompasses 15 diverse real-world scenarios and 5 evaluation tasks for online video understanding. Extensive experiments across three benchmarks demonstrate LiveStar's state-of-the-art performance, achieving an average 19.5% improvement in semantic correctness with 18.1% reduced timing difference compared to existing online Video-LLMs, while improving FPS by 12.0% across all five OmniStar tasks. Our model and dataset can be accessed at https://github.com/yzy-bupt/LiveStar.

Prior works have demonstrated zero-shot text-to-speech by using a generative language model on audio tokens obtained via a neural audio codec. It is still challenging, however, to adapt them to low-latency scenarios. In this paper, we present LiveSpeech - a fully autoregressive language model-based approach for zero-shot text-to-speech, enabling low-latency streaming of the output audio. To allow multiple token prediction within a single decoding step, we propose (1) using adaptive codebook loss weights that consider codebook contribution in each frame and focus on hard instances, and (2) grouping codebooks and processing groups in parallel. Experiments show our proposed models achieve competitive results to state-of-the-art baselines in terms of content accuracy, speaker similarity, audio quality, and inference speed while being suitable for low-latency streaming applications.

Recently, large language models (LLMs) have demonstrated superior performance across various tasks by adhering to scaling laws, which significantly increase model size. However, the huge computation overhead during inference hinders the deployment in industrial applications. Many works leverage traditional compression approaches to boost model inference, but these always introduce additional training costs to restore the performance and the pruning results typically show noticeable performance drops compared to the original model when aiming for a specific level of acceleration. To address these issues, we propose a fine-grained token-wise pruning approach for the LLMs, which presents a learnable router to adaptively identify the less important tokens and skip them across model blocks to reduce computational cost during inference. To construct the router efficiently, we present a search-based sparsity scheduler for pruning sparsity allocation, a trainable router combined with our proposed four low-dimensional factors as input and three proposed losses. We conduct extensive experiments across different benchmarks on different LLMs to demonstrate the superiority of our method. Our approach achieves state-of-the-art (SOTA) pruning results, surpassing other existing pruning methods. For instance, our method outperforms BlockPruner and ShortGPT by approximately 10 points on both LLaMA2-7B and Qwen1.5-7B in accuracy retention at comparable token sparsity levels.

Large language models have been widely adopted across different tasks, but their auto-regressive generation nature often leads to inefficient resource utilization during inference. While batching is commonly used to increase throughput, performance gains plateau beyond a certain batch size, especially with smaller models, a phenomenon that existing literature typically explains as a shift to the compute-bound regime. In this paper, through an in-depth GPU-level analysis, we reveal that large-batch inference remains memory-bound, with most GPU compute capabilities underutilized due to DRAM bandwidth saturation as the primary bottleneck. To address this, we propose a Batching Configuration Advisor (BCA) that optimizes memory allocation, reducing GPU memory requirements with minimal impact on throughput. The freed memory and underutilized GPU compute capabilities can then be leveraged by concurrent workloads. Specifically, we use model replication to improve serving throughput and GPU utilization. Our findings challenge conventional assumptions about LLM inference, offering new insights and practical strategies for improving resource utilization, particularly for smaller language models.

Training language models on long sequence data is a demanding requirement for enhancing the model's capability on complex tasks, e.g., long-chain reasoning. However, as the sequence length scales up, the memory cost for storing activation values becomes huge during the Backpropagation (BP) process, even with the application of gradient checkpointing technique. To tackle this challenge, we propose a memory-efficient and exact BP method called StreamBP, which performs a linear decomposition of the chain rule along the sequence dimension in a layer-wise manner, significantly reducing the memory cost of activation values and logits. The proposed method is applicable to common objectives such as SFT, GRPO, and DPO. From an implementation perspective, StreamBP achieves less computational FLOPs and faster BP speed by leveraging the causal structure of the language model. Compared to gradient checkpointing, StreamBP scales up the maximum sequence length of BP by 2.8-5.5 times larger, while using comparable or even less BP time. Note that StreamBP's sequence length scaling ability can be directly transferred to batch size scaling for accelerating training. We further develop a communication-efficient distributed StreamBP to effectively support multi-GPU training and broaden its applicability. Our code can be easily integrated into the training pipeline of any transformer models and is available at https://github.com/Ledzy/StreamBP.

Large language models (LLMs) demonstrate remarkable capabilities, but their broad deployment is limited by significant computational resource demands, particularly energy consumption during inference. Static, one-model-fits-all inference strategies are often inefficient, as they do not exploit the diverse range of available models or adapt to varying query requirements. This paper presents GreenServ, a dynamic, context-aware routing framework that optimizes the trade-off between inference accuracy and energy efficiency. GreenServ extracts lightweight contextual features from each query, including task type, semantic cluster, and text complexity, and routes queries to the most suitable model from a heterogeneous pool, based on observed accuracy and energy usage. We employ a multi-armed bandit approach to learn adaptive routing policies online. This approach operates under partial feedback, eliminates the need for extensive offline calibration, and streamlines the integration of new models into the inference pipeline. We evaluated GreenServ across five benchmark tasks and a pool of 16 contemporary open-access LLMs. Experimental results show that GreenServ consistently outperforms static (single-model) and random baselines. In particular, compared to random routing, GreenServ achieved a 22% increase in accuracy while reducing cumulative energy consumption by 31%. Finally, we evaluated GreenServ with RouterBench, achieving an average accuracy of 71.7% with a peak accuracy of 75.7%. All artifacts are open-source and available here: https://github.com/TZData1/llm-inference-router{GitHub}

Most evaluations of External Memory Module assume a static setting: memory is built offline and queried at a fixed state. In practice, memory is streaming: new facts arrive continuously, insertions interleave with retrievals, and the memory state evolves while the model is serving queries. In this regime, accuracy and cost are governed by the full memory lifecycle, which encompasses the ingestion, maintenance, retrieval, and integration of information into generation. We present Neuromem, a scalable testbed that benchmarks External Memory Modules under an interleaved insertion-and-retrieval protocol and decomposes its lifecycle into five dimensions including memory data structure, normalization strategy, consolidation policy, query formulation strategy, and context integration mechanism. Using three representative datasets LOCOMO, LONGMEMEVAL, and MEMORYAGENTBENCH, Neuromem evaluates interchangeable variants within a shared serving stack, reporting token-level F1 and insertion/retrieval latency. Overall, we observe that performance typically degrades as memory grows across rounds, and time-related queries remain the most challenging category. The memory data structure largely determines the attainable quality frontier, while aggressive compression and generative integration mechanisms mostly shift cost between insertion and retrieval with limited accuracy gain.

We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference. 3D convolutional neural networks (CNNs) are accurate at video recognition but require large computation and memory budgets and do not support online inference, making them difficult to work on mobile devices. We propose a three-step approach to improve computational efficiency while substantially reducing the peak memory usage of 3D CNNs. First, we design a video network search space and employ neural architecture search to generate efficient and diverse 3D CNN architectures. Second, we introduce the Stream Buffer technique that decouples memory from video clip duration, allowing 3D CNNs to embed arbitrary-length streaming video sequences for both training and inference with a small constant memory footprint. Third, we propose a simple ensembling technique to improve accuracy further without sacrificing efficiency. These three progressive techniques allow MoViNets to achieve state-of-the-art accuracy and efficiency on the Kinetics, Moments in Time, and Charades video action recognition datasets. For instance, MoViNet-A5-Stream achieves the same accuracy as X3D-XL on Kinetics 600 while requiring 80% fewer FLOPs and 65% less memory. Code will be made available at https://github.com/tensorflow/models/tree/master/official/vision.

Speculative decoding (SD) has become a popular technique to accelerate Large Language Model (LLM) inference, yet its real-world effectiveness remains unclear as prior evaluations rely on research prototypes and unrealistically small batch sizes. We present, to our knowledge, the first systematic study of SD on a production-grade and widely deployed inference engine (vLLM), covering multiple SD variants (n-gram, EAGLE/EAGLE-3, Draft-Model, Multi-Token Prediction) across diverse workloads, model scales, and batch sizes. We analyze key factors governing SD performance, and quantify a theoretical upper bound on SD speedup. Our results show that verification by the target model dominates the execution, while acceptance length varies markedly across output token positions, requests, and datasets. Comparing measured performance with theoretical bounds reveals substantial gaps between observed and theoretical upper bounds, and we leverage this observation to highlight new research opportunities that our study opens up in improving SD.

In Retrieval-Augmented Generation applications, the Information Retrieval part is central as it provides the contextual information that enables a Large Language Model to generate an appropriate and truthful response. High quality parsing and chunking are critical as efficient data segmentation directly impacts downstream tasks, i.e. Information Retrieval and answer generation. In this paper, we introduce ChunkNorris, a novel heuristic-based technique designed to optimise the parsing and chunking of PDF documents. Our approach does not rely on machine learning and employs a suite of simple yet effective heuristics to achieve high performance with minimal computational overhead. We demonstrate the efficiency of ChunkNorris through a comprehensive benchmark against existing parsing and chunking methods, evaluating criteria such as execution time, energy consumption, and retrieval accuracy. We propose an open-access dataset to produce our results. ChunkNorris outperforms baseline and more advanced techniques, offering a practical and efficient alternative for Information Retrieval tasks. Therefore, this research highlights the potential of heuristic-based methods for real-world, resource-constrained RAG use cases.

Large Language Models (LLMs) have demonstrated remarkable generation capabilities but often struggle to access up-to-date information, which can lead to hallucinations. Retrieval-Augmented Generation (RAG) addresses this issue by incorporating knowledge from external databases, enabling more accurate and relevant responses. Due to the context window constraints of LLMs, it is impractical to input the entire external database context directly into the model. Instead, only the most relevant information, referred to as chunks, is selectively retrieved. However, current RAG research faces three key challenges. First, existing solutions often select each chunk independently, overlooking potential correlations among them. Second, in practice the utility of chunks is non-monotonic, meaning that adding more chunks can decrease overall utility. Traditional methods emphasize maximizing the number of included chunks, which can inadvertently compromise performance. Third, each type of user query possesses unique characteristics that require tailored handling, an aspect that current approaches do not fully consider. To overcome these challenges, we propose a cost constrained retrieval optimization system CORAG for retrieval-augmented generation. We employ a Monte Carlo Tree Search (MCTS) based policy framework to find optimal chunk combinations sequentially, allowing for a comprehensive consideration of correlations among chunks. Additionally, rather than viewing budget exhaustion as a termination condition, we integrate budget constraints into the optimization of chunk combinations, effectively addressing the non-monotonicity of chunk utility.

Generative Large Language Models (LLMs) have demonstrated remarkable results for a wide range of tasks. However, deploying these models for inference has been a significant challenge due to their unprecedented resource requirements. This has forced existing deployment frameworks to use multi-GPU inference pipelines, which are often complex and costly, or to use smaller and less performant models. In this work, we demonstrate that the main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, specifically for single batch inference. While quantization has emerged as a promising solution by representing model weights with reduced precision, previous efforts have often resulted in notable performance degradation. To address this, we introduce SqueezeLLM, a post-training quantization framework that not only enables lossless compression to ultra-low precisions of up to 3-bit, but also achieves higher quantization performance under the same memory constraint. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format. When applied to the LLaMA models, our 3-bit quantization significantly reduces the perplexity gap from the FP16 baseline by up to 2.1x as compared to the state-of-the-art methods with the same memory requirement. Furthermore, when deployed on an A6000 GPU, our quantized models achieve up to 2.3x speedup compared to the baseline. Our code is open-sourced and available online.

While long-context large language models (LLMs) exhibit remarkable document processing capabilities, their prohibitively high training costs often hinder customized applications. To mitigate this issue, we propose Sequential Chunk-wise Optimization (SeCO), a memory-efficient training paradigm that partitions lengthy inputs into manageable chunks. Each chunk independently constructs its computational graph and performs localized backpropagation, ensuring that only one chunk's forward activations are stored in memory. Building on SeCO, we further introduce Sparse Chunk-wise Optimization (SpaCO), which reduces computational overhead by selectively propagating gradients to specific chunks and incorporates a carefully designed compensation factor to ensure unbiased gradient estimation. SpaCO decouples the computational cost of backpropagation from the context length, enabling training time to gradually converge to inference time as sequences become longer. Implemented as lightweight training wrappers, both SeCO and SpaCO offer substantial practical benefits. For example, when fine-tuning an 8B model with LoRA on a single RTX 3090 GPU, SeCO expands maximum sequence length from 1K to 16K tokens, while SpaCO demonstrates accelerated training speed -- achieving up to 3x faster than SeCO under the same experimental setup. These innovations provide new insights into optimizing long-context models, making them more accessible for practical applications. We have open-sourced the code at https://github.com/wenhaoli-xmu/seco{here}.

Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generation (RAG). We propose a cognitively inspired framework for efficient long-context inference based on chunk-wise compression and selective memory recall, rather than processing all raw tokens. The framework segments long inputs into chunks and encodes each chunk into compressed memory representations using a learned compressor. A gating module dynamically selects relevant memory blocks, which are then iteratively processed by a reasoning module with an evolving working memory to solve downstream tasks. The compressor and reasoner are jointly optimized via end-to-end reinforcement learning, while the gating module is trained separately as a classifier. Experimental results show that the proposed method achieves competitive accuracy on multi-hop reasoning benchmarks such as RULER-HQA, extrapolates context length from 7K to 1.75M tokens, and offers a favorable accuracy-efficiency trade-off compared to strong long-context baselines. In particular, it achieves up to a 2 times reduction in peak GPU memory usage and a 6 times inference speedup over MemAgent.

We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system. Delivering such a model presents numerous challenges: It should improve the performance when the input signal consists of overlapped speech, and must not hurt the speech recognition performance under all other acoustic conditions. Besides, this model must be tiny, fast, and perform inference in a streaming fashion, in order to have minimal impact on CPU, memory, battery and latency. We propose novel techniques to meet these multi-faceted requirements, including using a new asymmetric loss, and adopting adaptive runtime suppression strength. We also show that such a model can be quantized as a 8-bit integer model and run in realtime.

The quadratic complexity of the attention mechanism and the substantial memory footprint of the Key-Value (KV) cache present severe computational and memory challenges for Large Language Models (LLMs) processing long contexts. Existing retrieval-based methods often compromise semantic integrity through fixed-size chunking and suffer from inefficient linear scanning. In this paper, we propose LycheeCluster, a novel method for efficient KV cache management. LycheeCluster preserves local semantic coherence via boundary-aware chunking and constructs a recursive hierarchical index rooted in the triangle inequality. This design transforms cache retrieval from a linear scan into a theoretically bounded, logarithmic-time pruning process, while a lazy update strategy supports efficient streaming generation. Experiments demonstrate that LycheeCluster achieves up to a 3.6x end-to-end inference speedup with negligible degradation in model performance, outperforming state-of-the-art KV cache management methods (e.g., Quest, ClusterKV). We will release our code and kernels after publication.

In this paper, we introduce a novel low-latency inference framework for large language models (LLMs) inference which enables LLMs to perform inferences with incomplete prompts. By reallocating computational processes to prompt input phase, we achieve a substantial reduction in latency, thereby significantly enhancing the interactive experience for users of LLMs. The framework adeptly manages the visibility of the streaming prompt to the model, allowing it to infer from incomplete prompts or await additional prompts. Compared with traditional inference methods that utilize complete prompts, our approach demonstrates an average reduction of 59% in response latency on the MMLU-Pro dataset, while maintaining comparable accuracy. Additionally, our framework facilitates collaborative inference and output across different models. By employing an LLM for inference and a small language model (SLM) for output, we achieve an average 68% reduction in response latency, alongside a 5.5% improvement in accuracy on the MMLU-Pro dataset compared with the SLM baseline. For long prompts exceeding 20 sentences, the response latency can be reduced by up to 93%.