This survey provides a systematic review of resource-efficient techniques for Large Language Models (LLMs), addressing challenges related to computational, memory, energy, financial, and network resource usage. The paper categorizes methods based on their focus and applicability across the LLM lifecycle, including architecture design, pre-training, fine-tuning, and system design. It introduces a nuanced classification of resource efficiency techniques by specific resource types, revealing intricate relationships between resources and optimization strategies. A standardized set of evaluation metrics and datasets is presented to enable consistent and fair comparisons across models and techniques. The survey also identifies open research areas and offers a comprehensive overview of current state-of-the-art methods, aiming to guide researchers and practitioners in developing more sustainable and efficient LLMs. Additionally, the paper provides a structured taxonomy of resource-efficient LLM techniques, standardizes evaluation metrics, and highlights key challenges and future research directions in the field. The survey emphasizes the importance of resource efficiency in LLMs, particularly given their significant resource demands and environmental impact. It discusses various challenges, including low parallelism in auto-regressive generation, quadratic complexity in self-attention layers, scaling laws, generalization, system design, ethical concerns, and the need for comprehensive metrics. The paper also explores recent research efforts in developing resource-efficient LLMs, highlighting the need for systematic standardization and comprehensive summarization frameworks. The survey concludes with a detailed discussion of the key contributions, including a comprehensive overview of resource-efficient techniques, systematic categorization by resource type, standardization of evaluation metrics, and identification of open challenges and future research directions. The paper is structured into sections covering preliminary concepts, taxonomy, architecture design, pre-training, fine-tuning, inference, system design, technique categorization, benchmarking, open challenges, and conclusion. The survey aims to provide a foundational reference for researchers and practitioners, enabling the development of more sustainable and efficient LLMs in a rapidly evolving landscape.This survey provides a systematic review of resource-efficient techniques for Large Language Models (LLMs), addressing challenges related to computational, memory, energy, financial, and network resource usage. The paper categorizes methods based on their focus and applicability across the LLM lifecycle, including architecture design, pre-training, fine-tuning, and system design. It introduces a nuanced classification of resource efficiency techniques by specific resource types, revealing intricate relationships between resources and optimization strategies. A standardized set of evaluation metrics and datasets is presented to enable consistent and fair comparisons across models and techniques. The survey also identifies open research areas and offers a comprehensive overview of current state-of-the-art methods, aiming to guide researchers and practitioners in developing more sustainable and efficient LLMs. Additionally, the paper provides a structured taxonomy of resource-efficient LLM techniques, standardizes evaluation metrics, and highlights key challenges and future research directions in the field. The survey emphasizes the importance of resource efficiency in LLMs, particularly given their significant resource demands and environmental impact. It discusses various challenges, including low parallelism in auto-regressive generation, quadratic complexity in self-attention layers, scaling laws, generalization, system design, ethical concerns, and the need for comprehensive metrics. The paper also explores recent research efforts in developing resource-efficient LLMs, highlighting the need for systematic standardization and comprehensive summarization frameworks. The survey concludes with a detailed discussion of the key contributions, including a comprehensive overview of resource-efficient techniques, systematic categorization by resource type, standardization of evaluation metrics, and identification of open challenges and future research directions. The paper is structured into sections covering preliminary concepts, taxonomy, architecture design, pre-training, fine-tuning, inference, system design, technique categorization, benchmarking, open challenges, and conclusion. The survey aims to provide a foundational reference for researchers and practitioners, enabling the development of more sustainable and efficient LLMs in a rapidly evolving landscape.