Coleman Hooper

Sehoon Kim, Coleman Hooper, Amir Gholami et al. · berkeley

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 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 available at https://github.com/SqueezeAILab/SqueezeLLM.

Sehoon Kim, Coleman Hooper, Thanakul Wattanawong et al.

Recent advances in state-of-the-art DNN architecture design have been moving toward Transformer models. These models achieve superior accuracy across a wide range of applications. This trend has been consistent over the past several years since Transformer models were originally introduced. However, the amount of compute and bandwidth required for inference of recent Transformer models is growing at a significant rate, and this has made their deployment in latency-sensitive applications challenging. As such, there has been an increased focus on making Transformer models more efficient, with methods that range from changing the architecture design, all the way to developing dedicated domain-specific accelerators. In this work, we survey different approaches for efficient Transformer inference, including: (i) analysis and profiling of the bottlenecks in existing Transformer architectures and their similarities and differences with previous convolutional models; (ii) implications of Transformer architecture on hardware, including the impact of non-linear operations such as Layer Normalization, Softmax, and GELU, as well as linear operations, on hardware design; (iii) approaches for optimizing a fixed Transformer architecture; (iv) challenges in finding the right mapping and scheduling of operations for Transformer models; and (v) approaches for optimizing Transformer models by adapting the architecture using neural architecture search. Finally, we perform a case study by applying the surveyed optimizations on Gemmini, the open-source, full-stack DNN accelerator generator, and we show how each of these approaches can yield improvements, compared to previous benchmark results on Gemmini. Among other things, we find that a full-stack co-design approach with the aforementioned methods can result in up to 88.7x speedup with a minimal performance degradation for Transformer inference.

Ying Sheng, Shiyi Cao, Dacheng Li et al.

The "pretrain-then-finetune" paradigm is commonly adopted in the deployment of large language models. Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method, is often employed to adapt a base model to a multitude of tasks, resulting in a substantial collection of LoRA adapters derived from one base model. We observe that this paradigm presents significant opportunities for batched inference during serving. To capitalize on these opportunities, we present S-LoRA, a system designed for the scalable serving of many LoRA adapters. S-LoRA stores all adapters in the main memory and fetches the adapters used by the currently running queries to the GPU memory. To efficiently use the GPU memory and reduce fragmentation, S-LoRA proposes Unified Paging. Unified Paging uses a unified memory pool to manage dynamic adapter weights with different ranks and KV cache tensors with varying sequence lengths. Additionally, S-LoRA employs a novel tensor parallelism strategy and highly optimized custom CUDA kernels for heterogeneous batching of LoRA computation. Collectively, these features enable S-LoRA to serve thousands of LoRA adapters on a single GPU or across multiple GPUs with a small overhead. Compared to state-of-the-art libraries such as HuggingFace PEFT and vLLM (with naive support of LoRA serving), S-LoRA can improve the throughput by up to 4 times and increase the number of served adapters by several orders of magnitude. As a result, S-LoRA enables scalable serving of many task-specific fine-tuned models and offers the potential for large-scale customized fine-tuning services. The code is available at https://github.com/S-LoRA/S-LoRA

Lutfi Eren Erdogan, Nicholas Lee, Siddharth Jha et al.

Recent large language models (LLMs) have enabled the development of advanced agentic systems that can integrate various tools and APIs to fulfill user queries through function calling. However, the deployment of these LLMs on the edge has not been explored since they typically require cloud-based infrastructure due to their substantial model size and computational demands. To this end, we present TinyAgent, an end-to-end framework for training and deploying task-specific small language model agents capable of function calling for driving agentic systems at the edge. We first show how to enable accurate function calling for open-source models via the LLMCompiler framework. We then systematically curate a high-quality dataset for function calling, which we use to fine-tune two small language models, TinyAgent-1.1B and 7B. For efficient inference, we introduce a novel tool retrieval method to reduce the input prompt length and utilize quantization to further accelerate the inference speed. As a driving application, we demonstrate a local Siri-like system for Apple's MacBook that can execute user commands through text or voice input. Our results show that our models can achieve, and even surpass, the function-calling capabilities of larger models like GPT-4-Turbo, while being fully deployed at the edge. We open-source our dataset, models, and installable package and provide a demo video for our MacBook assistant agent.

Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh et al.

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios has been highly restricted due to the significant inference latency associated with these models. This is particularly pronounced due to the autoregressive nature of generative LLM inference, where tokens are generated sequentially since each token depends on all previous output tokens. It is therefore challenging to achieve any token-level parallelism, making inference extremely memory-bound. In this work, we propose SPEED, which improves inference efficiency by speculatively executing multiple future tokens in parallel with the current token using predicted values based on early-layer hidden states. For Transformer decoders that employ parameter sharing, the memory operations for the tokens executing in parallel can be amortized, which allows us to accelerate generative LLM inference. We demonstrate the efficiency of our method in terms of latency reduction relative to model accuracy and demonstrate how speculation allows for training deeper decoders with parameter sharing with minimal runtime overhead.

Monishwaran Maheswaran, Rishabh Tiwari, Yuezhou Hu et al. · berkeley

Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inference, and this motivates techniques to improve the performance-cost ratio. Among these techniques, Speculative Decoding accelerates inference by employing a fast but inaccurate draft model to autoregressively propose tokens, which are then verified in parallel by a more capable target model. However, due to unnecessary rejections caused by token mismatches in semantically equivalent steps, traditional token-level Speculative Decoding struggles in reasoning tasks. Although recent works have shifted to step-level semantic verification, which improve efficiency by accepting or rejecting entire reasoning steps, existing step-level methods still regenerate many rejected steps with little improvement, wasting valuable target compute. To address this challenge, we propose Arbitrage, a novel step-level speculative generation framework that routes generation dynamically based on the relative advantage between draft and target models. Instead of applying a fixed acceptance threshold, Arbitrage uses a lightweight router trained to predict when the target model is likely to produce a meaningfully better step. This routing approximates an ideal Arbitrage Oracle that always chooses the higher-quality step, achieving near-optimal efficiency-accuracy trade-offs. Across multiple mathematical reasoning benchmarks, Arbitrage consistently surpasses prior step-level Speculative Decoding baselines, reducing inference latency by up to $\sim2\times$ at matched accuracy.

Yuezhou Hu, Harman Singh, Monishwaran Maheswaran et al. · tsinghua

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel. However, state-of-the-art block-wise dLLMs rely on a "remasking" mechanism that decodes only the most confident tokens and discards the rest, effectively wasting computation. We demonstrate that recycling computation from the discarded tokens is beneficial, as these tokens retain contextual information useful for subsequent decoding iterations. In light of this, we propose Residual Context Diffusion (RCD), a module that converts these discarded token representations into contextual residuals and injects them back for the next denoising step. RCD uses a decoupled two-stage training pipeline to bypass the memory bottlenecks associated with backpropagation. We validate our method on both long CoT reasoning (SDAR) and short CoT instruction following (LLaDA) models. We demonstrate that a standard dLLM can be efficiently converted to the RCD paradigm with merely ~1 billion tokens. RCD consistently improves frontier dLLMs by 5-10 points in accuracy with minimal extra computation overhead across a wide range of benchmarks. Notably, on the most challenging AIME tasks, RCD nearly doubles baseline accuracy and attains up to 4-5x fewer denoising steps at equivalent accuracy levels.

Monishwaran Maheswaran, Leon Lakhani, Zhongzhu Zhou et al.

We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without external correction, repeated evolution accelerates collapse toward narrow modes, while the uniform use of a high-cost model wastes compute and quickly becomes economically impractical. We introduce Squeeze Evolve, a unified multi-model orchestration framework for verifier-free evolutionary inference. Our approach is guided by a simple principle: allocate model capability where it has the highest marginal utility. Stronger models are reserved for high-impact stages, while cheaper models handle the other stages at much lower costs. This principle addresses diversity and cost-efficiency jointly while remaining lightweight. Squeeze Evolve naturally supports open-source, closed-source, and mixed-model deployments. Across AIME 2025, HMMT 2025, LiveCodeBench V6, GPQA-Diamond, ARC-AGI-V2, and multimodal vision benchmarks, such as MMMU-Pro and BabyVision, Squeeze Evolve consistently improves the cost-capability frontier over single-model evolution and achieves new state-of-the-art results on several tasks. Empirically, Squeeze Evolve reduces API cost by up to $\sim$3$\times$ and increases fixed-budget serving throughput by up to $\sim$10$\times$. Moreover, on discovery tasks, Squeeze Evolve is the first verifier-free evolutionary method to match, and in some cases exceed, the performance of verifier-based evolutionary methods.

Haocheng Xi, Harman Singh, Yuezhou Hu et al. · berkeley

Block-wise diffusion language models (DLMs) generate multiple tokens in any order, offering a promising alternative to the autoregressive decoding pipeline. However, they still remain bottlenecked by memory-bound attention in long-context scenarios. Naive sparse attention fails on DLMs due to a KV Inflation problem, where different queries select different prefix positions, making the union of accessed KV pages large. To address this, we observe that between consecutive denoising steps, only a small fraction of active tokens exhibit significant hidden-state changes, while the majority of stable tokens remain nearly constant. Based on this insight, we propose LOSA (Locality-aware Sparse Attention), which reuses cached prefix-attention results for stable tokens and applies sparse attention only to active tokens. This substantially shrinks the number of KV indices that must be loaded, yielding both higher speedup and higher accuracy. Across multiple block-wise DLMs and benchmarks, LOSA preserves near-dense accuracy while significantly improving efficiency, achieving up to +9 points in average accuracy at aggressive sparsity levels while maintaining 1.54x lower attention density. It also achieves up to 4.14x attention speedup on RTX A6000 GPUs, demonstrating the effectiveness of the proposed method.

Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh et al.

Emerging Large Language Model (LLM) applications require long input context in order to perform complex tasks like document analysis and code generation. For these long context length applications, the length of the input prompt poses a significant challenge in terms of inference efficiency since the inference costs increase linearly with sequence length. However, for many of these applications, much of the context in the prompt is fixed across different user inputs, thereby providing the opportunity to perform offline optimizations in order to process user inputs quickly, as they are received. We propose Squeezed Attention to accelerate LLM applications where a large portion of the input context is fixed. We first leverage K-means clustering offline to group the keys for the fixed context based on semantic similarity and represent each cluster with a single centroid value. During inference, we compare query tokens from the user input with the centroids to predict which keys from the fixed context are semantically relevant, and then compute exact attention using only the important keys, thereby reducing bandwidth and computational costs. We also present a hierarchical version of our algorithm which can reduce the complexity of attention from linear to logarithmic with respect to the fixed context length. We evaluate our method on long-context benchmarks including LongBench, where it achieves a 3.1$\times$ reduction in KV budget with no noticeable accuracy loss and up to an 8$\times$ reduction with only a 0.5 point accuracy gap for the LLaMA-2-7B-32K, LWM-Text-Chat-1M, and Longchat-7B-v1.5-32K models. Futhermore, we implement kernels for centroid comparison and sparse FlashAttention with important keys, achieving more than 4$\times$ speedups during both the prefill and generation phases for long-context inference. Our code is available at https://github.com/SqueezeAILab/SqueezedAttention.

Coleman Hooper, Sehoon Kim, Suhong Moon et al.

Test-time compute scaling has emerged as a new axis along which to improve model accuracy, where additional computation is used at inference time to allow the model to think longer for more challenging problems. One promising approach for test-time compute scaling is search against a process reward model, where a model generates multiple potential candidates at each step of the search, and these partial trajectories are then scored by a separate reward model in order to guide the search process. The diversity of trajectories in the tree search process affects the accuracy of the search, since increasing diversity promotes more exploration. However, this diversity comes at a cost, as divergent trajectories have less KV sharing, which means they consume more memory and slow down the search process. Previous search methods either do not perform sufficient exploration, or else explore diverse trajectories but have high latency. We address this challenge by proposing Efficient Tree Search (ETS), which promotes KV sharing by pruning redundant trajectories while maintaining necessary diverse trajectories. ETS incorporates a linear programming cost model to promote KV cache sharing by penalizing the number of nodes retained, while incorporating a semantic coverage term into the cost model to ensure that we retain trajectories which are semantically different. We demonstrate how ETS can achieve 1.8$\times$ reduction in average KV cache size during the search process, leading to 1.4$\times$ increased throughput relative to prior state-of-the-art methods, with minimal accuracy degradation and without requiring any custom kernel implementation. Code is available at: https://github.com/SqueezeAILab/ETS.

Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh et al.

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a promising approach for compressing KV cache activations; however, existing solutions fail to represent activations accurately in sub-4-bit precision. Our work, KVQuant, facilitates low precision KV cache quantization by incorporating several novel methods: (i) Per-Channel Key Quantization, where we adjust the dimension along which we quantize the Key activations to better match the distribution; (ii) Pre-RoPE Key Quantization, where we quantize Key activations before the rotary positional embedding to mitigate its impact on quantization; (iii) Non-Uniform KV Cache Quantization, where we derive per-layer sensitivity-weighted non-uniform datatypes that better represent the distributions; and (iv) Per-Vector Dense-and-Sparse Quantization, where we isolate outliers separately for each vector to minimize skews in quantization ranges. By applying our method to the LLaMA, Llama-2, Llama-3, and Mistral models, we achieve < 0.1 perplexity degradation with 3-bit quantization on both Wikitext-2 and C4, outperforming existing approaches. Our method enables serving LLaMA-7B with a context length of up to 1 million on a single A100-80GB GPU and up to 10 million on an 8-GPU system. We develop custom CUDA kernels for KVQuant, showing that we can achieve up to ~1.7x speedups, compared to baseline fp16 matrix-vector multiplications, for the LLaMA-7B model.

Coleman Hooper, Sebastian Zhao, Luca Manolache et al.

Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks. While these models have attained high accuracy by leveraging additional computation at test time, they need to generate long chain-of-thought reasoning in order to think before answering, which requires generating thousands of tokens. While sparse attention methods can help reduce the KV cache pressure induced by this long autoregressive reasoning, these methods can introduce errors which disrupt the reasoning process. Additionally, prior methods often pre-process the input to make it easier to identify the important prompt tokens when computing attention during generation, and this pre-processing is challenging to perform online for newly generated reasoning tokens. Our work addresses these challenges by introducing Multipole Attention, which accelerates autoregressive reasoning by only computing exact attention for the most important tokens, while maintaining approximate representations for the remaining tokens. Our method first performs clustering to group together semantically similar key vectors, and then uses the cluster centroids both to identify important key vectors and to approximate the remaining key vectors in order to retain high accuracy. We design a fast cluster update process to quickly re-cluster the input and previously generated tokens, thereby allowing for accelerating attention to the previous output tokens. We evaluate our method using emerging LRMs such as Qwen-8B, demonstrating that our approach can maintain accuracy on complex reasoning tasks even with aggressive attention sparsity settings. We also provide kernel implementations to demonstrate the practical efficiency gains from our method, achieving up to 4.5$\times$ speedup for attention in long-context reasoning applications. Our code is available at https://github.com/SqueezeAILab/MultipoleAttention.

Amir Gholami, Zhewei Yao, Sehoon Kim et al.

The availability of unprecedented unsupervised training data, along with neural scaling laws, has resulted in an unprecedented surge in model size and compute requirements for serving/training LLMs. However, the main performance bottleneck is increasingly shifting to memory bandwidth. Over the past 20 years, peak server hardware FLOPS has been scaling at 3.0x/2yrs, outpacing the growth of DRAM and interconnect bandwidth, which have only scaled at 1.6 and 1.4 times every 2 years, respectively. This disparity has made memory, rather than compute, the primary bottleneck in AI applications, particularly in serving. Here, we analyze encoder and decoder Transformer models and show how memory bandwidth can become the dominant bottleneck for decoder models. We argue for a redesign in model architecture, training, and deployment strategies to overcome this memory limitation.

Minseo Kim, Coleman Hooper, Aditya Tomar et al.

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and coding. Autoregressive Language Models (ARMs), which generate tokens sequentially conditioned on all previous tokens, have been the predominant paradigm for LLMs. However, while these networks have achieved high accuracy across a range of downstream tasks, they exhibit low arithmetic intensity due to the inherent sequential dependency with next-token prediction. Recently, Diffusion Language Models (DLMs) have emerged as a promising alternative architecture. DLMs generate output text in parallel, breaking the limitations of sequential dependency. However, the performance implications of DLMs relative to commonly deployed ARMs are not fully understood. In this work, we present a comprehensive performance study analyzing the performance characteristics of ARMs and DLMs, using both theoretical analysis and profiling data to characterize the trade-offs between these approaches. We illustrate that although DLMs exhibit higher arithmetic intensity compared to ARMs because of their capability to utilize parallelism across sequence lengths, they fail to scale effectively to longer contexts. We then explore DLMs with block-wise decoding, outlining how this approach allows for increased arithmetic intensity, while still scaling well to long contexts (similar to ARMs). We also show interesting trade-offs for batched inference, where we find that ARMs exhibit superior throughput, as they benefit more from parallelism across sequences in the batch. Finally, we highlight opportunities for accelerating DLM inference, and, in particular, highlight the importance of reducing the number of sampling steps for allowing open-source DLMs to provide improved latency relative to ARMs.

Coleman Hooper, Thierry Tambe, Gu-Yeon Wei

This work analyzes how attention-based Bidirectional Long Short-Term Memory (BLSTM) models adapt to noise-augmented speech. We identify crucial components for noise adaptation in BLSTM models by freezing model components during fine-tuning. We first freeze larger model subnetworks and then pursue a fine-grained freezing approach in the encoder after identifying its importance for noise adaptation. The first encoder layer is shown to be crucial for noise adaptation, and the weights are shown to be more important than the other layers. Appreciable accuracy benefits are identified when fine-tuning on a target noisy environment from a model pretrained with noisy speech relative to fine-tuning from a model pretrained with only clean speech when tested on the target noisy environment. For this analysis, we produce our own dataset augmentation tool and it is open-sourced to encourage future efforts in exploring noise adaptation in ASR.

Rishabh Tiwari, Haocheng Xi, Aditya Tomar et al.

Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings, creating a growing need for fast and efficient long-context inference. In these scenarios, the Key-Value (KV) cache is the primary bottleneck in terms of both GPU memory and latency, as the full KV cache must be loaded for each decoding step. While speculative decoding is a widely accepted technique to accelerate autoregressive decoding, existing methods often struggle to achieve significant speedups due to inefficient KV cache optimization strategies and result in low acceptance rates. To address these challenges, we propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration. QuantSpec maintains high acceptance rates ($>$90%) and reliably provides consistent end-to-end speedups upto $\sim2.5\times$, outperforming other self-speculative decoding methods that use sparse KV cache for long-context LLM inference. QuantSpec also reduces the memory requirements by $\sim 1.3\times$ compared to these alternatives.

Siddharth Jha, Coleman Hooper, Xiaoxuan Liu et al.

Many applications must provide low-latency LLM service to users or risk unacceptable user experience. However, over-provisioning resources to serve fluctuating request patterns is often prohibitively expensive. In this work, we present a best-effort serving system that employs deep reinforcement learning to adjust service quality based on the task distribution and system load. Our best-effort system can maintain availability with over 10x higher client request rates, serves above 96% of peak performance 4.1x more often, and serves above 98% of peak performance 2.3x more often than static serving on unpredictable workloads. Our learned router is robust to shifts in both the arrival and task distribution. Compared to static serving, learned best-effort serving allows for cost-efficient serving through increased hardware utility. Additionally, we argue that learned best-effort LLM serving is applicable in wide variety of settings and provides application developers great flexibility to meet their specific needs.

Wonjun Kang, Kevin Galim, Seunghyuk Oh et al.

While most autoregressive LLMs are constrained to one-by-one decoding, diffusion LLMs (dLLMs) have attracted growing interest for their potential to dramatically accelerate inference through parallel decoding. Despite this promise, the conditional independence assumption in dLLMs causes parallel decoding to ignore token dependencies, inevitably degrading generation quality when these dependencies are strong. However, existing works largely overlook these inherent challenges, and evaluations on standard benchmarks (e.g., math and coding) are not sufficient to capture the quality degradation caused by parallel decoding. To address this gap, we first provide an information-theoretic analysis of parallel decoding. We then conduct case studies on analytically tractable synthetic list operations from both data distribution and decoding strategy perspectives, offering quantitative insights that highlight the fundamental limitations of parallel decoding. Building on these insights, we propose ParallelBench, the first benchmark specifically designed for dLLMs, featuring realistic tasks that are trivial for humans and autoregressive LLMs yet exceptionally challenging for dLLMs under parallel decoding. Using ParallelBench, we systematically analyze both dLLMs and autoregressive LLMs, revealing that: (i) dLLMs under parallel decoding can suffer dramatic quality degradation in real-world scenarios, and (ii) current parallel decoding strategies struggle to adapt their degree of parallelism based on task difficulty, thus failing to achieve meaningful speedup without compromising quality. Our findings underscore the pressing need for innovative decoding methods that can overcome the current speed-quality trade-off. We release our benchmark to help accelerate the development of truly efficient dLLMs.

Thierry Tambe, Coleman Hooper, Lillian Pentecost et al.

Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to resource-constrained edge platforms with strict latency requirements. We present EdgeBERT, an in-depth algorithm-hardware co-design for latency-aware energy optimization for multi-task NLP. EdgeBERT employs entropy-based early exit predication in order to perform dynamic voltage-frequency scaling (DVFS), at a sentence granularity, for minimal energy consumption while adhering to a prescribed target latency. Computation and memory footprint overheads are further alleviated by employing a calibrated combination of adaptive attention span, selective network pruning, and floating-point quantization. Furthermore, in order to maximize the synergistic benefits of these algorithms in always-on and intermediate edge computing settings, we specialize a 12nm scalable hardware accelerator system, integrating a fast-switching low-dropout voltage regulator (LDO), an all-digital phase-locked loop (ADPLL), as well as, high-density embedded non-volatile memories (eNVMs) wherein the sparse floating-point bit encodings of the shared multi-task parameters are carefully stored. Altogether, latency-aware multi-task NLP inference acceleration on the EdgeBERT hardware system generates up to 7x, 2.5x, and 53x lower energy compared to the conventional inference without early stopping, the latency-unbounded early exit approach, and CUDA adaptations on an Nvidia Jetson Tegra X2 mobile GPU, respectively.