Related papers: Anda: Unlocking Efficient LLM Inference with a Var…
Training LLMs presents significant memory challenges due to growing size of data, weights, and optimizer states. Techniques such as data and model parallelism, gradient checkpointing, and offloading strategies address this issue but are…
The inference of Large language models (LLMs) requires immense computation and memory resources. To curtail these costs, quantisation has merged as a promising solution, but existing LLM quantisation mainly focuses on 8-bit. In this work,…
Large Language Models (LLMs) have become extremely potent instruments with exceptional capacities for comprehending and producing human-like text in a wide range of applications. However, the increasing size and complexity of LLMs present…
Loom (LM), a hardware inference accelerator for Convolutional Neural Networks (CNNs) is presented. In LM every bit of data precision that can be saved translates to proportional performance gains. Specifically, for convolutional layers LM's…
To overcome the burden on the memory size and bandwidth due to ever-increasing size of large language models (LLMs), aggressive weight quantization has been recently studied, while lacking research on quantizing activations. In this paper,…
Transformer-based large language models (LLMs) have demonstrated remarkable performance across a wide range of real-world tasks, but their inference cost remains prohibitively high due to the quadratic complexity of attention and the memory…
Augmented Large Language Models (LLMs) enhance the capabilities of standalone LLMs by integrating external data sources through API calls. In interactive LLM applications, efficient scheduling is crucial for maintaining low request…
Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or…
Federated fine-tuning (FedFT) provides an effective paradigm for fine-tuning large language models (LLMs) in privacy-sensitive scenarios. However, practical deployment remains challenging due to the limited resources on end devices.…
Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed as two major strategies. However, both approaches have…
Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with…
Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Although floating-point…
Large language models (LLMs), based on transformer architectures, have revolutionized numerous domains within artificial intelligence, science, and engineering due to their exceptional scalability and adaptability. However, the exponential…
The growing computational demands of training large language models (LLMs) necessitate more efficient methods. Quantized training presents a promising solution by enabling low-bit arithmetic operations to reduce these costs. While FP8…
Large language models (LLMs) have shown immense potential across various domains, but their high memory requirements and inference costs remain critical challenges for deployment. Post-training quantization (PTQ) has emerged as a promising…
Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more memory to maintain first- and second-order moments than SGD. While recent works such as…
The advent of ultra-low-bit LLM models (1/1.58/2-bit), which match the perplexity and end-task performance of their full-precision counterparts using the same model size, is ushering in a new era of LLM inference for resource-constrained…
In recent years, Large Language Models (LLMs) through Transformer structures have dominated many machine learning tasks, especially text processing. However, these models require massive amounts of data for training and induce high resource…
LLMs' performance on complex tasks is still unsatisfactory. A key issue is that presently LLMs learn in a data-driven schema, while the instructions about these complex tasks are both scarce and hard to collect or construct. On the…
Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…