CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios

Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache compression methods typically focus on quantization and token pruning, which have compression limits, and excessive sparsity can lead to severe performance degradation. Other methods design new architectures with less KV overhead but require significant training overhead. To address the above two drawbacks, we further explore the redundancy in the channel dimension and apply an architecture-level design with minor training costs. Therefore, we introduce CSKV, a training-efficient Channel Shrinking technique for KV cache compression: (1) We first analyze the singular value distribution of the KV cache, revealing significant redundancy and compression potential along the channel dimension. Based on this observation, we propose using low-rank decomposition for key and value layers and storing the low-dimension features. (2) To preserve model performance, we introduce a bi-branch KV cache, including a window-based full-precision KV cache and a low-precision compressed KV cache. (3) To reduce the training costs, we minimize the layer-wise reconstruction loss for the compressed KV cache instead of retraining the entire LLMs. Extensive experiments show that CSKV can reduce the memory overhead of the KV cache by 80% while maintaining the model's long-context capability. Moreover, we show that our method can be seamlessly combined with quantization to further reduce the memory overhead, achieving a compression ratio of up to 95%.

Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding

Fourier features based positional encoding (PE) is commonly used in machine learning tasks that involve learning high-frequency features from low-dimensional inputs, such as 3D view synthesis and time series regression with neural tangent kernels. Despite their effectiveness, existing PEs require manual, empirical adjustment of crucial hyperparameters, specifically the Fourier features, tailored to each unique task. Further, PEs face challenges in efficiently learning high-frequency functions, particularly in tasks with limited data. In this paper, we introduce sinusoidal PE (SPE), designed to efficiently learn adaptive frequency features closely aligned with the true underlying function. Our experiments demonstrate that SPE, without hyperparameter tuning, consistently achieves enhanced fidelity and faster training across various tasks, including 3D view synthesis, Text-to-Speech generation, and 1D regression. SPE is implemented as a direct replacement for existing PEs. Its plug-and-play nature lets numerous tasks easily adopt and benefit from SPE.

DiTFastAttn: Attention Compression for Diffusion Transformer Models

Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to self-attention's quadratic complexity. We propose DiTFastAttn, a novel post-training compression method to alleviate DiT's computational bottleneck. We identify three key redundancies in the attention computation during DiT inference: 1. spatial redundancy, where many attention heads focus on local information; 2. temporal redundancy, with high similarity between neighboring steps' attention outputs; 3. conditional redundancy, where conditional and unconditional inferences exhibit significant similarity. To tackle these redundancies, we propose three techniques: 1. Window Attention with Residual Caching to reduce spatial redundancy; 2. Temporal Similarity Reduction to exploit the similarity between steps; 3. Conditional Redundancy Elimination to skip redundant computations during conditional generation. To demonstrate the effectiveness of DiTFastAttn, we apply it to DiT, PixArt-Sigma for image generation tasks, and OpenSora for video generation tasks. Evaluation results show that for image generation, our method reduces up to 88\% of the FLOPs and achieves up to 1.6x speedup at high resolution generation.

PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram

Real-time and high-performance 3D object detection plays a critical role in autonomous driving and robotics. Recent pillar-based 3D object detectors have gained significant attention due to their compact representation and low computational overhead, making them suitable for onboard deployment and quantization. However, existing pillar-based detectors still suffer from information loss along height dimension and large numerical distribution difference during pillar feature encoding (PFE), which severely limits their performance and quantization potential. To address above issue, we first unveil the importance of different input information during PFE and identify the height dimension as a key factor in enhancing 3D detection performance. Motivated by this observation, we propose a height-aware pillar feature encoder named PillarHist. Specifically, PillarHist statistics the discrete distribution of points at different heights within one pillar. This simple yet effective design greatly preserves the information along the height dimension while significantly reducing the computation overhead of the PFE. Meanwhile, PillarHist also constrains the arithmetic distribution of PFE input to a stable range, making it quantization-friendly. Notably, PillarHist operates exclusively within the PFE stage to enhance performance, enabling seamless integration into existing pillar-based methods without introducing complex operations. Extensive experiments show the effectiveness of PillarHist in terms of both efficiency and performance.

I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models

Post-training quantization (PTQ) serves as a potent technique to accelerate the inference of large language models (LLMs). Nonetheless, existing works still necessitate a considerable number of floating-point (FP) operations during inference, including additional quantization and de-quantization, as well as non-linear operators such as RMSNorm and Softmax. This limitation hinders the deployment of LLMs on the edge and cloud devices. In this paper, we identify the primary obstacle to integer-only quantization for LLMs lies in the large fluctuation of activations across channels and tokens in both linear and non-linear operations. To address this issue, we propose I-LLM, a novel integer-only fully-quantized PTQ framework tailored for LLMs. Specifically, (1) we develop Fully-Smooth Block-Reconstruction (FSBR) to aggressively smooth inter-channel variations of all activations and weights. (2) to alleviate degradation caused by inter-token variations, we introduce a novel approach called Dynamic Integer-only MatMul (DI-MatMul). This method enables dynamic quantization in full-integer matrix multiplication by dynamically quantizing the input and outputs with integer-only operations. (3) we design DI-ClippedSoftmax, DI-Exp, and DI-Normalization, which utilize bit shift to execute non-linear operators efficiently while maintaining accuracy. The experiment shows that our I-LLM achieves comparable accuracy to the FP baseline and outperforms non-integer quantization methods. For example, I-LLM can operate at W4A4 with negligible loss of accuracy. To our knowledge, we are the first to bridge the gap between integer-only quantization and LLMs. We've published our code on anonymous.4open.science, aiming to contribute to the advancement of this field.

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

Training diffusion models is always a computation-intensive task. In this paper, we introduce a novel speed-up method for diffusion model training, called, which is based on a closer look at time steps. Our key findings are: i) Time steps can be empirically divided into acceleration, deceleration, and convergence areas based on the process increment. ii) These time steps are imbalanced, with many concentrated in the convergence area. iii) The concentrated steps provide limited benefits for diffusion training. To address this, we design an asymmetric sampling strategy that reduces the frequency of steps from the convergence area while increasing the sampling probability for steps from other areas. Additionally, we propose a weighting strategy to emphasize the importance of time steps with rapid-change process increments. As a plug-and-play and architecture-agnostic approach, SpeeD consistently achieves 3-times acceleration across various diffusion architectures, datasets, and tasks. Notably, due to its simple design, our approach significantly reduces the cost of diffusion model training with minimal overhead. Our research enables more researchers to train diffusion models at a lower cost.

SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models

Large language models (LLMs) can now handle longer sequences of tokens, enabling complex tasks like book understanding and generating lengthy novels. However, the key-value (KV) cache required for LLMs consumes substantial memory as context length increasing, becoming the bottleneck for deployment. In this paper, we present a strategy called SKVQ, which stands for sliding-window KV cache quantization, to address the issue of extremely low bitwidth KV cache quantization. To achieve this, SKVQ rearranges the channels of the KV cache in order to improve the similarity of channels in quantization groups, and applies clipped dynamic quantization at the group level. Additionally, SKVQ ensures that the most recent window tokens in the KV cache are preserved with high precision. This helps maintain the accuracy of a small but important portion of the KV cache.SKVQ achieves high compression ratios while maintaining accuracy. Our evaluation on LLMs demonstrates that SKVQ surpasses previous quantization approaches, allowing for quantization of the KV cache to 2-bit keys and 1.5-bit values with minimal loss of accuracy. With SKVQ, it is possible to process context lengths of up to 1M on an 80GB memory GPU for a 7b model and up to 7 times faster decoding.

A Survey on Efficient Inference for Large Language Models

Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirements of LLM inference pose challenges for deployment in resource-constrained scenarios. Efforts within the field have been directed towards developing techniques aimed at enhancing the efficiency of LLM inference. This paper presents a comprehensive survey of the existing literature on efficient LLM inference. We start by analyzing the primary causes of the inefficient LLM inference, i.e., the large model size, the quadratic-complexity attention operation, and the auto-regressive decoding approach. Then, we introduce a comprehensive taxonomy that organizes the current literature into data-level, model-level, and system-level optimization. Moreover, the paper includes comparative experiments on representative methods within critical sub-fields to provide quantitative insights. Last but not least, we provide some knowledge summary and discuss future research directions.

PillarTrack: Redesigning Pillar-based Transformer Network for Single Object Tracking on Point Clouds

LiDAR-based 3D single object tracking (3D SOT) is a critical issue in robotics and autonomous driving. It aims to obtain accurate 3D BBox from the search area based on similarity or motion. However, existing 3D SOT methods usually follow the point-based pipeline, where the sampling operation inevitably leads to redundant or lost information, resulting in unexpected performance. To address these issues, we propose PillarTrack, a pillar-based 3D single object tracking framework. Firstly, we transform sparse point clouds into dense pillars to preserve the local and global geometrics. Secondly, we introduce a Pyramid-type Encoding Pillar Feature Encoder (PE-PFE) design to help the feature representation of each pillar. Thirdly, we present an efficient Transformer-based backbone from the perspective of modality differences. Finally, we construct our PillarTrack tracker based above designs. Extensive experiments on the KITTI and nuScenes dataset demonstrate the superiority of our proposed method. Notably, our method achieves state-of-the-art performance on the KITTI and nuScenes dataset and enables real-time tracking speed. We hope our work could encourage the community to rethink existing 3D SOT tracker designs.We will open source our code to the research community in https://github.com/StiphyJay/PillarTrack.

LLM Inference Unveiled: Survey and Roofline Model Insights

The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is vibrant, there hasn't been a concise framework that analyzes the various methods of LLM Inference to provide a clear understanding of this domain. Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model for systematic analysis of LLM inference techniques. This framework identifies the bottlenecks when deploying LLMs on hardware devices and provides a clear understanding of practical problems, such as why LLMs are memory-bound, how much memory and computation they need, and how to choose the right hardware. We systematically collate the latest advancements in efficient LLM inference, covering crucial areas such as model compression (e.g., Knowledge Distillation and Quantization), algorithm improvements (e.g., Early Exit and Mixture-of-Expert), and both hardware and system-level enhancements. Our survey stands out by analyzing these methods with roofline model, helping us understand their impact on memory access and computation. This distinctive approach not only showcases the current research landscape but also delivers valuable insights for practical implementation, positioning our work as an indispensable resource for researchers new to the field as well as for those seeking to deepen their understanding of efficient LLM deployment. The analyze tool, LLM-Viewer, is open-sourced.