The rapid evolution of large language models (LLMs) has revolutionized natural language processing (NLP) tasks such as text generation, translation, and comprehension. However, the increasing computational demands and inference costs of these models present significant challenges. This study investigates the dynamic and efficient utilization of pre-trained weights from open-sourced LLMs of varying parameter sizes to achieve an optimal balance between computational efficiency and task performance. Drawing inspiration from the dual-process theory of human cognition, we introduce StitchLLM: a dynamic model routing framework that employs a powerful bottom model to process all queries, and uses a lightweight routing mechanism to allocate computational resources appropriately. Our novel framework optimizes efficiency and maintains performance, leveraging a trainable stitching layer for seamless integration of decoder layers across different LLMs. Experimental results demonstrate that StitchLLM improves system throughput while minimizing performance degradation, offering a flexible solution for deploying LLMs in resource-constrained settings.

Rapid advancements over the years have helped machine learning models reach previously hard-to-achieve goals, sometimes even exceeding human capabilities. However, achieving desired accuracy comes at the cost of larger model sizes and increased computational demands. Thus, serving predictions from these models to meet any latency and cost requirements of applications remains a key challenge, despite recent work in building inference serving systems as well as algorithmic approaches that dynamically adapt models based on inputs. Our paper introduces a new form of dynamism, modality selection, where we adaptively choose modalities from inference inputs while maintaining the model quality. We introduce MOSEL, an automated inference serving system for multi-modal ML models that carefully picks input modalities per request based on user-defined performance and accuracy requirements. MOSEL exploits modality configurations extensively, improving system throughput by 3.6 × with an accuracy guarantee. It also reduces job completion times by 11× compared to modality-agnostic approaches.

Autoregressive Large Language Models (e.g., LLaMa, GPTs) are omnipresent achieving remarkable success in language understanding and generation. However, such impressive capability typically comes with a substantial model size, which presents significant challenges for autoregressive token-by-token generation. To mitigate computation overload incurred during generation, several early-exit and layer-dropping strategies have been proposed. Despite some promising success due to the redundancy across LLMs layers on metrics like Rough-L/BLUE, our careful knowledge-intensive evaluation unveils issues such as generation collapse, hallucination, and noticeable performance drop even at the trivial exit ratio of ~10-15% of layers. We attribute these errors primarily to ineffective handling of the KV cache through state copying during early exit. In this work, we observe the saturation of computationally expensive feed-forward blocks of LLM layers and propose FFN-SkipLLM, which is a novel fine-grained skip strategy for autoregressive LLMs. FFN-SkipLLM leverages an input-adaptive feed-forward skipping approach that can skip ~25-30% of FFN blocks of LLMs with marginal change in performance on knowledge-intensive generation tasks without any requirement to handle the KV cache. Our extensive experiments and ablation studies across benchmarks like MT-Bench, Factoid-QA, and variable-length text summarization illustrate how our simple and easy-to-use method can facilitate faster autoregressive decoding.