HarmoniCa: Harmonizing Training and Inference for Better Feature Cache in Diffusion Transformer Acceleration

Diffusion Transformers (DiTs) have gained prominence for outstanding scalability and extraordinary performance in generative tasks. However, their considerable inference costs impede practical deployment. The feature cache mechanism, which involves storing and retrieving redundant computations across timesteps, holds promise for reducing per-step inference time in diffusion models. Most existing caching methods for DiT are manually designed. Although the learning-based approach attempts to optimize strategies adaptively, it suffers from discrepancies between training and inference, which hampers both the performance and acceleration ratio. Upon detailed analysis, we pinpoint that these discrepancies primarily stem from two aspects: (1) Prior Timestep Disregard, where training ignores the effect of cache usage at earlier timesteps, and (2) Objective Mismatch, where the training target (align predicted noise in each timestep) deviates from the goal of inference (generate the high-quality image). To alleviate these discrepancies, we propose HarmoniCa, a novel method that Harmonizes training and inference with a novel learning-based Caching framework built upon Step-Wise Denoising Training (SDT) and Image Error Proxy-Guided Objective (IEPO). Compared to the traditional training paradigm, the newly proposed SDT maintains the continuity of the denoising process, enabling the model to leverage information from prior timesteps during training, similar to the way it operates during inference. Furthermore, we design IEPO, which integrates an efficient proxy mechanism to approximate the final image error caused by reusing the cached feature. Therefore, IEPO helps balance final image quality and cache utilization, resolving the issue of training that only considers the impact of cache usage on the predicted output at each timestep.

A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms

Large language models (LLMs) have achieved remarkable advancements in natural language processing, showcasing exceptional performance across various tasks. However, the expensive memory and computational requirements present significant challenges for their practical deployment. Low-bit quantization has emerged as a critical approach to mitigate these challenges by reducing the bit-width of model parameters, activations, and gradients, thus decreasing memory usage and computational demands. This paper presents a comprehensive survey of low-bit quantization methods tailored for LLMs, covering the fundamental principles, system implementations, and algorithmic strategies. An overview of basic concepts and new data formats specific to low-bit LLMs is first introduced, followed by a review of frameworks and systems that facilitate low-bit LLMs across various hardware platforms. Then, we categorize and analyze techniques and toolkits for efficient low-bit training and inference of LLMs. Finally, we conclude with a discussion of future trends and potential advancements of low-bit LLMs. Our systematic overview from basic, system, and algorithm perspectives can offer valuable insights and guidelines for future works to enhance the efficiency and applicability of LLMs through low-bit quantization.

OmniBal: Towards Fast Instruct-tuning for Vision-Language Models via Omniverse Computation Balance

Recently, vision-language instruct-tuning models have made significant progress due to their more comprehensive understanding of the world. In this work, we discovered that large-scale 3D parallel training on those models leads to an imbalanced computation load across different devices. The vision and language parts are inherently heterogeneous: their data distribution and model architecture differ significantly, which affects distributed training efficiency. We rebalanced the computational loads from data, model, and memory perspectives to address this issue, achieving more balanced computation across devices. These three components are not independent but are closely connected, forming an omniverse balanced training framework. Specifically, for the data, we grouped instances into new balanced mini-batches within and across devices. For the model, we employed a search-based method to achieve a more balanced partitioning. For memory optimization, we adaptively adjusted the re-computation strategy for each partition to utilize the available memory fully. We conducted extensive experiments to validate the effectiveness of our method. Compared with the open-source training code of InternVL-Chat, we significantly reduced GPU days, achieving about 1.8x speed-up. Our method's efficacy and generalizability were further demonstrated across various models and datasets. Codes will be released at https://github.com/ModelTC/OmniBal.

Temporal Feature Matters: A Framework for Diffusion Model Quantization

The Diffusion models, widely used for image generation, face significant challenges related to their broad applicability due to prolonged inference times and high memory demands. Efficient Post-Training Quantization (PTQ) is crucial to address these issues in traditional models. Unlike those models, diffusion models critically rely on the time-step $t$ for effective multi-round denoising. Typically, $t$ from the finite set $\{1, \ldots, T\}$ is encoded into a hypersensitive temporal feature by several modules, entirely independent of the sampling data. However, existing PTQ methods do not optimize these modules individually. Instead, they employ unsuitable reconstruction objectives and complex calibration methods, leading to significant disturbances in the temporal feature and denoising trajectory. To address these challenges, we introduce a novel quantization framework: 1)~TIB-based Maintenance: Based on our innovative Temporal Information Block~(TIB) definition, Temporal Information-aware Reconstruction~(TIAR) and Finite Set Calibration~(FSC) are developed to efficiently align full precision temporal features. 2)~Cache-based Maintenance: Instead of indirect and complex optimization for the related modules, pre-computing and caching quantized counterparts of temporal features are developed to minimize errors. 3)~Disturbance-aware Selection: Employ temporal feature errors to guide a fine-grained selection for superior maintenance. This framework preserves most of the temporal information and ensures high-quality end-to-end generation. Extensive testing on various datasets and diffusion models confirms our superior results. Notably, our approach closely matches the performance of the full-precision model under 4-bit quantization. Furthermore, the quantized SD-XL model achieves hardware acceleration of 2.20$\times$ on CPU and 5.76$\times$ on GPU demonstrating its efficiency.

ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models

The typical process for developing LLMs involves pre-training a general foundation model on massive data, followed by fine-tuning on task-specific data to create specialized experts. Serving these experts poses challenges, as loading all experts onto devices is impractical, and frequent switching between experts in response to user requests incurs substantial I/O costs, increasing latency and expenses. Previous approaches decompose expert weights into pre-trained model weights and residual delta weights, then quantize the delta weights to reduce model size. However, these methods often lead to significant quantization errors at extremely low bitwidths and assume the appropriate model for a user request is known in advance, which is not practical. To address these issues, we introduce ME-Switch, a memory-efficient expert switching framework for LLM serving. ME-Switch uses mixed-precision quantization, selectively quantizing non-salient input channels of delta weights to extremely low bits while keeping salient ones intact, significantly reducing storage demands while maintaining performance. Additionally, we develop a routing method that efficiently directs user queries to the most suitable expert by transforming the model selection problem into a domain classification problem. Extensive experiments show ME-Switch's promising memory efficiency and routing performance. For example, when serving three models from the Mistral-7B family, ME-Switch reduces model size by 1.74x while maintaining nearly lossless performance on instruction, mathematical reasoning, and code generation tasks. Furthermore, ME-Switch can efficiently serve 16 models from the Mistral-7B family on a single NVIDIA A100 GPU.

Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection

Lane detection (LD) plays a crucial role in enhancing the L2+ capabilities of autonomous driving, capturing widespread attention. The Post-Processing Quantization (PTQ) could facilitate the practical application of LD models, enabling fast speeds and limited memories without labeled data. However, prior PTQ methods do not consider the complex LD outputs that contain physical semantics, such as offsets, locations, etc., and thus cannot be directly applied to LD models. In this paper, we pioneeringly investigate semantic sensitivity to post-processing for lane detection with a novel Lane Distortion Score. Moreover, we identify two main factors impacting the LD performance after quantization, namely intra-head sensitivity and inter-head sensitivity, where a small quantization error in specific semantics can cause significant lane distortion. Thus, we propose a Selective Focus framework deployed with Semantic Guided Focus and Sensitivity Aware Selection modules, to incorporate post-processing information into PTQ reconstruction. Based on the observed intra-head sensitivity, Semantic Guided Focus is introduced to prioritize foreground-related semantics using a practical proxy. For inter-head sensitivity, we present Sensitivity Aware Selection, efficiently recognizing influential prediction heads and refining the optimization objectives at runtime. Extensive experiments have been done on a wide variety of models including keypoint-, anchor-, curve-, and segmentation-based ones. Our method produces quantized models in minutes on a single GPU and can achieve 6.4% F1 Score improvement on the CULane dataset.

LLM-QBench: A Benchmark Towards the Best Practice for Post-training Quantization of Large Language Models

Recent advancements in large language models (LLMs) are propelling us toward artificial general intelligence, thanks to their remarkable emergent abilities and reasoning capabilities. However, the substantial computational and memory requirements of LLMs limit their widespread adoption. Quan- tization, a key compression technique, offers a viable solution to mitigate these demands by compressing and accelerating LLMs, albeit with poten- tial risks to model accuracy. Numerous studies have aimed to minimize the accuracy loss associated with quantization. However, the quantization configurations in these studies vary and may not be optimized for hard- ware compatibility. In this paper, we focus on identifying the most effective practices for quantizing LLMs, with the goal of balancing performance with computational efficiency. For a fair analysis, we develop a quantization toolkit LLMC, and design four crucial principles considering the inference efficiency, quantized accuracy, calibration cost, and modularization. By benchmarking on various models and datasets with over 500 experiments, three takeaways corresponding to calibration data, quantization algorithm, and quantization schemes are derived. Finally, a best practice of LLM PTQ pipeline is constructed. All the benchmark results and the toolkit can be found at https://github.com/ModelTC/llmc.

Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes

Neural network sparsity has attracted many research interests due to its similarity to biological schemes and high energy efficiency. However, existing methods depend on long-time training or fine-tuning, which prevents large-scale applications. Recently, some works focusing on post-training sparsity (PTS) have emerged. They get rid of the high training cost but usually suffer from distinct accuracy degradation due to neglect of the reasonable sparsity rate at each layer. Previous methods for finding sparsity rates mainly focus on the training-aware scenario, which usually fails to converge stably under the PTS setting with limited data and much less training cost. In this paper, we propose a fast and controllable post-training sparsity (FCPTS) framework. By incorporating a differentiable bridge function and a controllable optimization objective, our method allows for rapid and accurate sparsity allocation learning in minutes, with the added assurance of convergence to a predetermined global sparsity rate. Equipped with these techniques, we can surpass the state-of-the-art methods by a large margin, e.g., over 30\% improvement for ResNet-50 on ImageNet under the sparsity rate of 80\%. Our plug-and-play code and supplementary materials are open-sourced at https://github.com/ModelTC/FCPTS.

2023 Low-Power Computer Vision Challenge (LPCVC) Summary

This article describes the 2023 IEEE Low-Power Computer Vision Challenge (LPCVC). Since 2015, LPCVC has been an international competition devoted to tackling the challenge of computer vision (CV) on edge devices. Most CV researchers focus on improving accuracy, at the expense of ever-growing sizes of machine models. LPCVC balances accuracy with resource requirements. Winners must achieve high accuracy with short execution time when their CV solutions run on an embedded device, such as Raspberry PI or Nvidia Jetson Nano. The vision problem for 2023 LPCVC is segmentation of images acquired by Unmanned Aerial Vehicles (UAVs, also called drones) after disasters. The 2023 LPCVC attracted 60 international teams that submitted 676 solutions during the submission window of one month. This article explains the setup of the competition and highlights the winners' methods that improve accuracy and shorten execution time.

ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding

Recent advancements in generative large language models (LLMs) have significantly boosted the performance in natural language processing tasks. However, their efficiency is hampered by the inherent limitations in autoregressive token generation. While parallel decoding with token tree verification, e.g., Medusa, has been proposed to improve decoding parallelism and efficiency, it often struggles with maintaining contextual relationships due to its independent token prediction approach and incurs significant verification overhead, especially with large tree sizes and batch processing. In this paper, we propose ProPD, an efficient LLM parallel decoding framework based on dynamic token tree pruning and generation. ProPD features an advanced early pruning mechanism to efficiently eliminate unpromising token sequences to improve verification efficiency. Additionally, it introduces a dynamic token tree generation algorithm to balance the computation and parallelism of the verification phase in real-time and maximize the overall efficiency across different batch sizes, sequence lengths, and tasks, etc. We verify ProPD across a diverse set of datasets, LLMs, and batch sizes and demonstrate ProPD consistently outperforms existing decoding algorithms by 1.1-3.2x.