An official website of the United States government
Recently, a new trend of exploring training sparsity has emerged, which remove parameters during training, leading to both training and inference efficiency improvement. This line of works primarily aims to obtain a single sparse model under a pre-defined large sparsity ratio. It leads to a static/fixed sparse inference model that is not capable of adjusting or re-configuring its computation complexity (i.e., inference structure, latency) after training for real-world varying and dynamic hardware resource availability. To enable such run-time or post-training network morphing, the concept of `dynamic inference' or `training-once-for-all' has been proposed to train a single network consisting of multiple sub-nets once, but each sub-net could perform the same inference function with different computing complexity. However, the traditional dynamic inference training method requires a joint training scheme with multi-objective optimization, which suffers from very large training overhead. In this work, for the first time, we propose a novel alternating sparse training (AST) scheme to train multiple sparse sub-nets for dynamic inference without extra training cost compared to the case of training a single sparse model from scratch. Furthermore, to mitigate the interference of weight update among sub-nets, we propose gradient correction within the inner-group iterations to reduce their weight update interference. We validate the proposed AST on multiple datasets against state-of-the-art sparse training method, which shows that AST achieves similar or better accuracy, but only needs to train once to get multiple sparse sub-nets with different sparsity ratios. More importantly, compared with the traditional joint training based dynamic inference training methodology, the large training overhead is completely eliminated without affecting the accuracy of each sub-net.
more »
« less
This content will become publicly available on July 1, 2026
LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences
Throughout its lifecycle, an LLM incurs significantly higher carbon emissions during inference than training. Inference requests vary in batch size, prompt length, and token generation, while cloud providers deploy heterogeneous GPU configurations to meet diverse service-level objectives. Unlike training, inference exhibits lower and highly variable hardware utilization, making equation-based carbon models unreliable. Existing network-based estimators lack accuracy, as they fail to account for the distinct prefill and decode phases, hardware-specific features, and realistic request distributions. We propose LLMCO2, a graph neural network (GNN)-based model, to improve the accuracy of LLM inference carbon footprint estimation by ~ 67% over prior approaches. Source code is available at https://github.com/fuzhenxiao/LLMCO2.
more »
« less
- Award ID(s):
- 2143120
- PAR ID:
- 10651574
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- ACM SIGEnergy Energy Informatics Review
- Volume:
- 5
- Issue:
- 2
- ISSN:
- 2770-5331
- Page Range / eLocation ID:
- 63 to 68
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract We present a novel deep neural network (DNN) training scheme and resistive RAM (RRAM) in-memory computing (IMC) hardware evaluation towards achieving high accuracy against RRAM device/array variations and enhanced robustness against adversarial input attacks. We present improved IMC inference accuracy results evaluated on state-of-the-art DNNs including ResNet-18, AlexNet, and VGG with binary, 2-bit, and 4-bit activation/weight precision for the CIFAR-10 dataset. These DNNs are evaluated with measured noise data obtained from three different RRAM-based IMC prototype chips. Across these various DNNs and IMC chip measurements, we show that our proposed hardware noise-aware DNN training consistently improves DNN inference accuracy for actual IMC hardware, up to 8% accuracy improvement for the CIFAR-10 dataset. We also analyze the impact of our proposed noise injection scheme on the adversarial robustness of ResNet-18 DNNs with 1-bit, 2-bit, and 4-bit activation/weight precision. Our results show up to 6% improvement in the robustness to black-box adversarial input attacks.more » « less
-
Training modern LLMs is extremely resource intensive, and customizing them for various deployment scenarios characterized by limited compute and memory resources through repeated training is impractical. In this paper, we introduce Flextron, a network architecture and post-training model optimization framework supporting flexible model deployment. The Flextron architecture utilizes a nested elastic structure to rapidly adapt to specific user-defined latency and accuracy targets during inference with no additional fine-tuning required. It is also input-adaptive, and can automatically route tokens through its sub-networks for improved performance and efficiency. We present a sample-efficient training method and associated routing algorithms for systematically transforming an existing trained LLM into a Flextron model. We evaluate Flextron on the GPT-3 and LLama-2 family of LLMs, and demonstrate superior performance over multiple end-to-end trained variants and other state-of-the-art elastic networks, all with a single pretraining run that consumes a mere 7.63% tokens compared to original pretraining.more » « less
-
null (Ed.)To deploy powerful deep neural network (DNN) into smart, but resource limited IoT devices, many prior works have been proposed to compress DNN to reduce the network size and computation complexity with negligible accuracy degradation, such as weight quantization, network pruning, convolution decomposition, etc. However, by utilizing conventional DNN compression methods, a smaller, but fixed, network is generated from a relative large background model to achieve resource limited hardware acceleration. However, such optimization lacks the ability to adjust its structure in real-time to adapt for a dynamic computing hardware resource allocation and workloads. In this paper, we mainly review our two prior works [13], [15] to tackle this challenge, discussing how to construct a dynamic DNN by means of either uniform or non-uniform sub-nets generation methods. Moreover, to generate multiple non-uniform sub-nets, [15] needs to fully retrain the background model for each sub-net individually, named as multi-path method. To reduce the training cost, in this work, we further propose a single-path sub-nets generation method that can sample multiple sub-nets in different epochs within one training round. The constructed dynamic DNN, consisting of multiple sub-nets, provides the ability to run-time trade-off the inference accuracy and latency according to hardware resources and environment requirements. In the end, we study the the dynamic DNNs with different sub-nets generation methods on both CIFAR-10 and ImageNet dataset. We also present the run-time tuning of accuracy and latency on both GPU and CPU.more » « less
-
raining modern large language models (LLMs) is extremely resource-intensive, and repeatedly customizing them for deployment scenarios with limited compute and memory is impractical. This paper introduces Flextron, a network architecture and post-training model optimization framework that supports flexible model deployment. Flextron uses a nested elastic structure that adapts rapidly to user-defined latency and accuracy targets during inference without requiring additional fine-tuning. It is also input-adaptive, automatically routing tokens through sub-networks for improved efficiency and performance. The authors propose a sample-efficient training method and routing algorithms to systematically transform an already-trained LLM into a Flextron model. Evaluation on the GPT-3 and LLaMA-2 families demonstrates Flextron’s superior performance over end-to-end trained variants and other state-of-the-art elastic networks, all with a single pretraining run that consumes only 7.63% of the tokens compared to original pretraining.more » « less
