Related papers: Puzzle: Distillation-Based NAS for Inference-Optim…

We introduce InfiFusion, an efficient training pipeline designed to integrate multiple domain-specialized Large Language Models (LLMs) into a single pivot model, effectively harnessing the strengths of each source model. Traditional fusion…

Large language models (LLMs) are computationally intensive. The computation workload and the memory footprint grow quadratically with the dimension (layer width). Most of LLMs' parameters come from the linear layers of the transformer…

Large language models (LLMs) deliver impressive performance but incur prohibitive memory and compute costs at deployment. Model pruning is an effective way to reduce these overheads, yet existing approaches face challenges: unstructured…

Large language model (LLM) pruning with fixed N:M structured sparsity significantly limits the expressivity of the sparse model, yielding sub-optimal performance. In contrast, supporting multiple N:M patterns to provide sparse…

This work elaborates on a High performance computing (HPC) architecture based on Simple Linux Utility for Resource Management (SLURM) [1] for deploying heterogeneous Large Language Models (LLMs) into a scalable inference engine. Dynamic…

Ensemble learning of LLMs has emerged as a promising alternative to enhance performance, but existing approaches typically treat models as black boxes, combining the inputs or final outputs while overlooking the rich internal…

Due to long generations, large language model (LLM) math reasoning demands significant computational resources and time. While many existing efficient inference methods have been developed with excellent performance preservation on language…

As large language models (LLMs) continue to grow in size, distributed inference has become increasingly important. Model-parallel strategies must now efficiently scale not only across multiple GPUs but also across multiple nodes. In this…

Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning in unfamiliar settings. This discrepancy suggests that standard fine-tuning pipelines may instill narrow, domain-specific heuristics…

Recently, large pre-trained models have significantly improved the performance of various Natural LanguageProcessing (NLP) tasks but they are expensive to serve due to long serving latency and large memory usage. To compress these models,…

Large language models (LLMs) are widely applied in chatbots, code generators, and search engines. Workload such as chain-of-throught, complex reasoning, agent services significantly increase the inference cost by invoke the model…

Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and…

The recent surge of open-source large language models (LLMs) enables developers to create AI-based solutions while maintaining control over aspects such as privacy and compliance, thereby providing governance and ownership of the model…

Large language models(LLMs) containing tens of billions of parameters (or even more) have demonstrated impressive capabilities in various NLP tasks. However, substantial model size poses challenges to training, inference, and deployment so…

Autoregressive inference in large transformer-based language models (LLMs) presents significant challenges for runtime efficiency, particularly during the decode phase where load imbalance across GPU shards can cause throughput degradation…

The integration of large language models (LLMs) into automated algorithm design has shown promising potential. A prevalent approach embeds LLMs within search routines to iteratively generate and refine candidate algorithms. However, most…

Large Language Models (LLMs) have gained popularity in recent years, driving up the demand for inference. LLM inference is composed of two phases with distinct characteristics: a compute-bound prefill phase followed by a memory-bound decode…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various fields, from natural language understanding to text generation. Compared to non-generative LLMs like BERT and DeBERTa, generative LLMs like GPT series and…

Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller task-specific models by either finetuning with human labels…

Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex…