LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

The inference of transformer-based large language models consists of two sequential stages: 1) a prefilling stage to compute the KV cache of prompts and generate the first token, and 2) a decoding stage to generate subsequent tokens. For long prompts, the KV cache must be computed for all tokens during the prefilling stage, which can significantly increase the time needed to generate the first token. Consequently, the prefilling stage may become a bottleneck in the generation process. An open question remains whether all prompt tokens are essential for generating the first token. To answer this, we introduce a novel method, LazyLLM, that selectively computes the KV for tokens important for the next token prediction in both the prefilling and decoding stages. Contrary to static pruning approaches that prune the prompt at once, LazyLLM allows language models to dynamically select different subsets of tokens from the context in different generation steps, even though they might be pruned in previous steps. Extensive experiments on standard datasets across various tasks demonstrate that LazyLLM is a generic method that can be seamlessly integrated with existing language models to significantly accelerate the generation without fine-tuning. For instance, in the multi-document question-answering task, LazyLLM accelerates the prefilling stage of the LLama 2 7B model by 2.34x while maintaining accuracy.

KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation

Large Language Model or LLM inference has two phases, the prompt (or prefill) phase to output the first token and the extension (or decoding) phase to the generate subsequent tokens. In this work, we propose an efficient parallelization scheme, KV-Runahead to accelerate the prompt phase. The key observation is that the extension phase generates tokens faster than the prompt phase because of key-value cache (KV-cache). Hence, KV-Runahead parallelizes the prompt phase by orchestrating multiple processes to populate the KV-cache and minimizes the time-to-first-token (TTFT). Dual-purposing the KV-cache scheme has two main benefits. Fist, since KV-cache is designed to leverage the causal attention map, we minimize computation and computation automatically. Second, since it already exists for the extension phase, KV-Runahead is easy to implement. We further propose context-level load-balancing to handle uneven KV-cache generation (due to the causal attention) and to optimize TTFT. Compared with an existing parallelization scheme such as tensor or sequential parallelization where keys and values are locally generated and exchanged via all-gather collectives, our experimental results demonstrate that KV-Runahead can offer over 1.4x and 1.6x speedups for Llama 7B and Falcon 7B respectively.

LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their intensive computational and memory requirements present challenges, especially for devices with limited DRAM capacity. This paper tackles the challenge of efficiently running LLMs that exceed the available DRAM capacity by storing the model parameters on flash memory but bringing them on demand to DRAM. Our method involves constructing an inference cost model that harmonizes with the flash memory behavior, guiding us to optimize in two critical areas: reducing the volume of data transferred from flash and reading data in larger, more contiguous chunks. Within this flash memory-informed framework, we introduce two principal techniques. First, "windowing'" strategically reduces data transfer by reusing previously activated neurons, and second, "row-column bundling", tailored to the sequential data access strengths of flash memory, increases the size of data chunks read from flash memory. These methods collectively enable running models up to twice the size of the available DRAM, with a 4-5x and 20-25x increase in inference speed compared to naive loading approaches in CPU and GPU, respectively. Our integration of sparsity awareness, context-adaptive loading, and a hardware-oriented design paves the way for effective inference of LLMs on devices with limited memory.

Prompting might be all you need to repair Compressed LLMs

Large language models (LLMs), while transformative for NLP, come with significant computational demands, underlining the need for efficient, training-free compression. Notably, despite the marked improvement in training-free compression for the largest of LLMs, our tests using LLaMA-7B and OPT-6.7b highlight a significant performance drop in several realistic downstream tasks. Investigation into the trade-off between resource-intensive post-compression re-training highlights the prospect of prompt-driven recovery as a lightweight adaption tool. However, existing studies, confined mainly to perplexity evaluations and simple tasks, fail to offer unequivocal confidence in the scalability and generalizability of prompting. We tackle this uncertainty in two key ways. First, we uncover the vulnerability of naive prompts in LLM compression as an over-reliance on a singular prompt per input. In response, we propose inference-time dynamic prompting (IDP), a mechanism that autonomously chooses from a set of curated prompts based on the context of each individual input. Second, we delve into a scientific understanding of why "prompting might be all you need post-LLM compression." Our findings suggest that compression does not irretrievably erase LLM model knowledge but displace it, necessitating a new inference path. IDP effectively redirects this path, enabling the model to tap into its inherent yet displaced knowledge and thereby recover performance. Empirical tests affirm the value of IDP, demonstrating an average performance improvement of 1.24% across nine varied tasks spanning multiple knowledge domains.

Streaming Anchor Loss: Augmenting Supervision with Temporal Significance

Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms. Hence, increasing the learning capacity of such streaming models (i.e., by adding more parameters) to improve the predictive power may not be viable for real-world tasks. In this work, we propose a new loss, Streaming Anchor Loss (SAL), to better utilize the given learning capacity by encouraging the model to learn more from essential frames. More specifically, our SAL and its focal variations dynamically modulate the frame-wise cross entropy loss based on the importance of the corresponding frames so that a higher loss penalty is assigned for frames within the temporal proximity of semantically critical events. Therefore, our loss ensures that the model training focuses on predicting the relatively rare but task-relevant frames. Experimental results with standard lightweight convolutional and recurrent streaming networks on three different speech based detection tasks demonstrate that SAL enables the model to learn the overall task more effectively with improved accuracy and latency, without any additional data, model parameters, or architectural changes.

eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models

Since Large Language Models or LLMs have demonstrated high-quality performance on many complex language tasks, there is a great interest in bringing these LLMs to mobile devices for faster responses and better privacy protection. However, the size of LLMs (i.e., billions of parameters) requires highly effective compression to fit into storage-limited devices. Among many compression techniques, weight-clustering, a form of non-linear quantization, is one of the leading candidates for LLM compression, and supported by modern smartphones. Yet, its training overhead is prohibitively significant for LLM fine-tuning. Especially, Differentiable KMeans Clustering, or DKM, has shown the state-of-the-art trade-off between compression ratio and accuracy regression, but its large memory complexity makes it nearly impossible to apply to train-time LLM compression. In this paper, we propose a memory-efficient DKM implementation, eDKM powered by novel techniques to reduce the memory footprint of DKM by orders of magnitudes. For a given tensor to be saved on CPU for the backward pass of DKM, we compressed the tensor by applying uniquification and sharding after checking if there is no duplicated tensor previously copied to CPU. Our experimental results demonstrate that \prjname can fine-tune and compress a pretrained LLaMA 7B model from 12.6 GB to 2.5 GB (3bit/weight) with the Alpaca dataset by reducing the train-time memory footprint of a decoder layer by 130$\times$, while delivering good accuracy on broader LLM benchmarks (i.e., 77.7% for PIQA, 66.1% for Winograde, and so on).

Flexible Keyword Spotting based on Homogeneous Audio-Text Embedding

Spotting user-defined/flexible keywords represented in text frequently uses an expensive text encoder for joint analysis with an audio encoder in an embedding space, which can suffer from heterogeneous modality representation (i.e., large mismatch) and increased complexity. In this work, we propose a novel architecture to efficiently detect arbitrary keywords based on an audio-compliant text encoder which inherently has homogeneous representation with audio embedding, and it is also much smaller than a compatible text encoder. Our text encoder converts the text to phonemes using a grapheme-to-phoneme (G2P) model, and then to an embedding using representative phoneme vectors, extracted from the paired audio encoder on rich speech datasets. We further augment our method with confusable keyword generation to develop an audio-text embedding verifier with strong discriminative power. Experimental results show that our scheme outperforms the state-of-the-art results on Libriphrase hard dataset, increasing Area Under the ROC Curve (AUC) metric from 84.21% to 92.7% and reducing Equal-Error-Rate (EER) metric from 23.36% to 14.4%.

Matching Latent Encoding for Audio-Text based Keyword Spotting

Using audio and text embeddings jointly for Keyword Spotting (KWS) has shown high-quality results, but the key challenge of how to semantically align two embeddings for multi-word keywords of different sequence lengths remains largely unsolved. In this paper, we propose an audio-text-based end-to-end model architecture for flexible keyword spotting (KWS), which builds upon learned audio and text embeddings. Our architecture uses a novel dynamic programming-based algorithm, Dynamic Sequence Partitioning (DSP), to optimally partition the audio sequence into the same length as the word-based text sequence using the monotonic alignment of spoken content. Our proposed model consists of an encoder block to get audio and text embeddings, a projector block to project individual embeddings to a common latent space, and an audio-text aligner containing a novel DSP algorithm, which aligns the audio and text embeddings to determine if the spoken content is the same as the text. Experimental results show that our DSP is more effective than other partitioning schemes, and the proposed architecture outperformed the state-of-the-art results on the public dataset in terms of Area Under the ROC Curve (AUC) and Equal-Error-Rate (EER) by 14.4 % and 28.9%, respectively.

PDP: Parameter-free Differentiable Pruning is All You Need

DNN pruning is a popular way to reduce the size of a model, improve the inference latency, and minimize the power consumption on DNN accelerators. However, existing approaches might be too complex, expensive or ineffective to apply to a variety of vision/language tasks, DNN architectures and to honor structured pruning constraints. In this paper, we propose an efficient yet effective train-time pruning scheme, Parameter-free Differentiable Pruning (PDP), which offers state-of-the-art qualities in model size, accuracy, and training cost. PDP uses a dynamic function of weights during training to generate soft pruning masks for the weights in a parameter-free manner for a given pruning target. While differentiable, the simplicity and efficiency of PDP make it universal enough to deliver state-of-the-art random/structured/channel pruning results on various vision and natural language tasks. For example, for MobileNet-v1, PDP can achieve 68.2% top-1 ImageNet1k accuracy at 86.6% sparsity, which is 1.7% higher accuracy than those from the state-of-the-art algorithms. Also, PDP yields over 83.1% accuracy on Multi-Genre Natural Language Inference with 90% sparsity for BERT, while the next best from the existing techniques shows 81.5% accuracy. In addition, PDP can be applied to structured pruning, such as N:M pruning and channel pruning. For 1:4 structured pruning of ResNet18, PDP improved the top-1 ImageNet1k accuracy by over 3.6% over the state-of-the-art. For channel pruning of ResNet50, PDP reduced the top-1 ImageNet1k accuracy by 0.6% from the state-of-the-art.

R^2: Range Regularization for Model Compression and Quantization

Model parameter regularization is a widely used technique to improve generalization, but also can be used to shape the weight distributions for various purposes. In this work, we shed light on how weight regularization can assist model quantization and compression techniques, and then propose range regularization (R^2) to further boost the quality of model optimization by focusing on the outlier prevention. By effectively regulating the minimum and maximum weight values from a distribution, we mold the overall distribution into a tight shape so that model compression and quantization techniques can better utilize their limited numeric representation powers. We introduce L-inf regularization, its extension margin regularization and a new soft-min-max regularization to be used as a regularization loss during full-precision model training. Coupled with state-of-the-art quantization and compression techniques, models trained with R^2 perform better on an average, specifically at lower bit weights with 16x compression ratio. We also demonstrate that R^2 helps parameter constrained models like MobileNetV1 achieve significant improvement of around 8% for 2 bit quantization and 7% for 1 bit compression.