LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression

In long context scenarios, large language models (LLMs) face three main challenges: higher computational/financial cost, longer latency, and inferior performance. Some studies reveal that the performance of LLMs depends on both the density and the position of the key information (question relevant) in the input prompt. Inspired by these findings, we propose LongLLMLingua for prompt compression towards improving LLMs' perception of the key information to simultaneously address the three challenges. We conduct evaluation on a wide range of long context scenarios including single-/multi-document QA, few-shot learning, summarization, synthetic tasks, and code completion. The experimental results show that LongLLMLingua compressed prompt can derive higher performance with much less cost. The latency of the end-to-end system is also reduced. For example, on NaturalQuestions benchmark, LongLLMLingua gains a performance boost of up to 17.1% over the original prompt with ~4x fewer tokens as input to GPT-3.5-Turbo. It can derive cost savings of \$28.5 and \$27.4 per 1,000 samples from the LongBench and ZeroScrolls benchmark, respectively. Additionally, when compressing prompts of ~10k tokens at a compression rate of 2x-10x, LongLLMLingua can speed up the end-to-end latency by 1.4x-3.8x. Our code is available at https://aka.ms/LLMLingua.

LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts fed to LLMs are becoming increasingly lengthy, even exceeding tens of thousands of tokens. To accelerate model inference and reduce cost, this paper presents LLMLingua, a coarse-to-fine prompt compression method that involves a budget controller to maintain semantic integrity under high compression ratios, a token-level iterative compression algorithm to better model the interdependence between compressed contents, and an instruction tuning based method for distribution alignment between language models. We conduct experiments and analysis over four datasets from different scenarios, i.e., GSM8K, BBH, ShareGPT, and Arxiv-March23; showing that the proposed approach yields state-of-the-art performance and allows for up to 20x compression with little performance loss. Our code is available at https://aka.ms/LLMLingua.

ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation

While language-guided image manipulation has made remarkable progress, the challenge of how to instruct the manipulation process faithfully reflecting human intentions persists. An accurate and comprehensive description of a manipulation task using natural language is laborious and sometimes even impossible, primarily due to the inherent uncertainty and ambiguity present in linguistic expressions. Is it feasible to accomplish image manipulation without resorting to external cross-modal language information? If this possibility exists, the inherent modality gap would be effortlessly eliminated. In this paper, we propose a novel manipulation methodology, dubbed ImageBrush, that learns visual instructions for more accurate image editing. Our key idea is to employ a pair of transformation images as visual instructions, which not only precisely captures human intention but also facilitates accessibility in real-world scenarios. Capturing visual instructions is particularly challenging because it involves extracting the underlying intentions solely from visual demonstrations and then applying this operation to a new image. To address this challenge, we formulate visual instruction learning as a diffusion-based inpainting problem, where the contextual information is fully exploited through an iterative process of generation. A visual prompting encoder is carefully devised to enhance the model's capacity in uncovering human intent behind the visual instructions. Extensive experiments show that our method generates engaging manipulation results conforming to the transformations entailed in demonstrations. Moreover, our model exhibits robust generalization capabilities on various downstream tasks such as pose transfer, image translation and video inpainting.

Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference

Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length. In this work, we propose a constraint-aware and ranking-distilled token pruning method ToP, which selectively removes unnecessary tokens as input sequence passes through layers, allowing the model to improve online inference speed while preserving accuracy. ToP overcomes the limitation of inaccurate token importance ranking in the conventional self-attention mechanism through a ranking-distilled token distillation technique, which distills effective token rankings from the final layer of unpruned models to early layers of pruned models. Then, ToP introduces a coarse-to-fine pruning approach that automatically selects the optimal subset of transformer layers and optimizes token pruning decisions within these layers through improved $L_0$ regularization. Extensive experiments on GLUE benchmark and SQuAD tasks demonstrate that ToP outperforms state-of-the-art token pruning and model compression methods with improved accuracy and speedups. ToP reduces the average FLOPs of BERT by 8.1x while achieving competitive accuracy on GLUE, and provides a real latency speedup of up to 7.4x on an Intel CPU.

Full Parameter Fine-tuning for Large Language Models with Limited Resources

Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) but demand massive GPU resources for training. Lowering the threshold for LLMs training would encourage greater participation from researchers, benefiting both academia and society. While existing approaches have focused on parameter-efficient fine-tuning, which tunes or adds a small number of parameters, few have addressed the challenge of tuning the full parameters of LLMs with limited resources. In this work, we propose a new optimizer, LOw-Memory Optimization (LOMO), which fuses the gradient computation and the parameter update in one step to reduce memory usage. By integrating LOMO with existing memory saving techniques, we reduce memory usage to 10.8% compared to the standard approach (DeepSpeed solution). Consequently, our approach enables the full parameter fine-tuning of a 65B model on a single machine with 8 RTX 3090, each with 24GB memory.

End-to-End Word-Level Pronunciation Assessment with MASK Pre-training

Pronunciation assessment is a major challenge in the computer-aided pronunciation training system, especially at the word (phoneme)-level. To obtain word (phoneme)-level scores, current methods usually rely on aligning components to obtain acoustic features of each word (phoneme), which limits the performance of assessment to the accuracy of alignments. Therefore, to address this problem, we propose a simple yet effective method, namely \underline{M}asked pre-training for \underline{P}ronunciation \underline{A}ssessment (MPA). Specifically, by incorporating a mask-predict strategy, our MPA supports end-to-end training without leveraging any aligning components and can solve misalignment issues to a large extent during prediction. Furthermore, we design two evaluation strategies to enable our model to conduct assessments in both unsupervised and supervised settings. Experimental results on SpeechOcean762 dataset demonstrate that MPA could achieve better performance than previous methods, without any explicit alignment. In spite of this, MPA still has some limitations, such as requiring more inference time and reference text. They expect to be addressed in future work.

Accurate and Structured Pruning for Efficient Automatic Speech Recognition

Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural networks, such as Transformer and Conformer. However, these models typically have large model sizes and high inference costs, posing a challenge to deploy on resource-limited devices. In this paper, we propose a novel compression strategy that leverages structured pruning and knowledge distillation to reduce the model size and inference cost of the Conformer model while preserving high recognition performance. Our approach utilizes a set of binary masks to indicate whether to retain or prune each Conformer module, and employs L0 regularization to learn the optimal mask values. To further enhance pruning performance, we use a layerwise distillation strategy to transfer knowledge from unpruned to pruned models. Our method outperforms all pruning baselines on the widely used LibriSpeech benchmark, achieving a 50% reduction in model size and a 28% reduction in inference cost with minimal performance loss.

An AMR-based Link Prediction Approach for Document-level Event Argument Extraction

Recent works have introduced Abstract Meaning Representation (AMR) for Document-level Event Argument Extraction (Doc-level EAE), since AMR provides a useful interpretation of complex semantic structures and helps to capture long-distance dependency. However, in these works AMR is used only implicitly, for instance, as additional features or training signals. Motivated by the fact that all event structures can be inferred from AMR, this work reformulates EAE as a link prediction problem on AMR graphs. Since AMR is a generic structure and does not perfectly suit EAE, we propose a novel graph structure, Tailored AMR Graph (TAG), which compresses less informative subgraphs and edge types, integrates span information, and highlights surrounding events in the same document. With TAG, we further propose a novel method using graph neural networks as a link prediction model to find event arguments. Our extensive experiments on WikiEvents and RAMS show that this simpler approach outperforms the state-of-the-art models by 3.63pt and 2.33pt F1, respectively, and do so with reduced 56% inference time. The code is availabel at https://github.com/ayyyq/TARA.

EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention

Vision transformers have shown great success due to their high model capabilities. However, their remarkable performance is accompanied by heavy computation costs, which makes them unsuitable for real-time applications. In this paper, we propose a family of high-speed vision transformers named EfficientViT. We find that the speed of existing transformer models is commonly bounded by memory inefficient operations, especially the tensor reshaping and element-wise functions in MHSA. Therefore, we design a new building block with a sandwich layout, i.e., using a single memory-bound MHSA between efficient FFN layers, which improves memory efficiency while enhancing channel communication. Moreover, we discover that the attention maps share high similarities across heads, leading to computational redundancy. To address this, we present a cascaded group attention module feeding attention heads with different splits of the full feature, which not only saves computation cost but also improves attention diversity. Comprehensive experiments demonstrate EfficientViT outperforms existing efficient models, striking a good trade-off between speed and accuracy. For instance, our EfficientViT-M5 surpasses MobileNetV3-Large by 1.9% in accuracy, while getting 40.4% and 45.2% higher throughput on Nvidia V100 GPU and Intel Xeon CPU, respectively. Compared to the recent efficient model MobileViT-XXS, EfficientViT-M2 achieves 1.8% superior accuracy, while running 5.8x/3.7x faster on the GPU/CPU, and 7.4x faster when converted to ONNX format. Code and models are available at https://github.com/microsoft/Cream/tree/main/EfficientViT.

Learned Focused Plenoptic Image Compression with Microimage Preprocessing and Global Attention

Focused plenoptic cameras can record spatial and angular information of the light field (LF) simultaneously with higher spatial resolution relative to traditional plenoptic cameras, which facilitate various applications in computer vision. However, the existing plenoptic image compression methods present ineffectiveness to the captured images due to the complex micro-textures generated by the microlens relay imaging and long-distance correlations among the microimages. In this paper, a lossy end-to-end learning architecture is proposed to compress the focused plenoptic images efficiently. First, a data preprocessing scheme is designed according to the imaging principle to remove the sub-aperture image ineffective pixels in the recorded light field and align the microimages to the rectangular grid. Then, the global attention module with large receptive field is proposed to capture the global correlation among the feature maps using pixel-wise vector attention computed in the resampling process. Also, a new image dataset consisting of 1910 focused plenoptic images with content and depth diversity is built to benefit training and testing. Extensive experimental evaluations demonstrate the effectiveness of the proposed approach. It outperforms intra coding of HEVC and VVC by an average of 62.57% and 51.67% bitrate reduction on the 20 preprocessed focused plenoptic images, respectively. Also, it achieves 18.73% bitrate saving and generates perceptually pleasant reconstructions compared to the state-of-the-art end-to-end image compression methods, which benefits the applications of focused plenoptic cameras greatly. The dataset and code are publicly available at https://github.com/VincentChandelier/GACN.