Related papers: APEX: An Extensible and Dynamism-Aware Simulator f…

Large language models have led to state-of-the-art accuracies across a range of tasks. However, training these models efficiently is challenging for two reasons: a) GPU memory capacity is limited, making it impossible to fit large models on…

Modern out-of-order processors have increased capacity to exploit instruction level parallelism (ILP) and memory level parallelism (MLP), e.g., by using wide superscalar pipelines and vector execution units, as well as deep buffers for…

The explosive arrival of OpenAI's ChatGPT has fueled the globalization of large language model (LLM), which consists of billions of pretrained parameters that embodies the aspects of syntax and semantics. HyperAccel introduces latency…

Serving Large Language Models (LLMs) in production faces significant challenges from highly variable request patterns and severe resource fragmentation in serverless clusters. Current systems rely on static pipeline configurations that…

RAPID-LLM is a unified performance modeling framework for large language model (LLM) training and inference on GPU clusters. It couples a DeepFlow-based frontend that generates hardware-aware, operator-level Chakra execution traces from an…

Efficient parallelism is necessary for achieving low-latency, high-throughput inference with large language models (LLMs). Tensor parallelism (TP) is the state-of-the-art method for reducing LLM response latency, however GPU communications…

Large Language Models (LLMs) such as GPT-4 and Llama have shown remarkable capabilities in a variety of software engineering tasks. Despite the advancements, their practical deployment faces challenges, including high financial costs, long…

Careful parametrization of networking protocols is crucial to maximize the performance of low-power wireless systems and ensure that stringent application requirements can be met. This is a non-trivial task involving thorough…

Extending the context length (i.e., the maximum supported sequence length) of LLMs is of paramount significance. To facilitate long context training of LLMs, sequence parallelism has emerged as an essential technique, which scatters each…

Modern scientific discovery increasingly relies on high-performance computing for complex modeling and simulation. A key challenge in improving parallel program performance is efficiently mapping tasks to processors and data to memory, a…

This work evaluates the potential of large language models (LLMs) to power digital assistants capable of complex action execution. These assistants rely on pre-trained programming knowledge to execute multi-step goals by composing objects…

Assessing the capabilities of large multimodal models (LMMs) often requires the creation of ad-hoc evaluations. Currently, building new benchmarks requires tremendous amounts of manual work for each specific analysis. This makes the…

Recently, there has been an extensive research effort in building efficient large language model (LLM) inference serving systems. These efforts not only include innovations in the algorithm and software domains but also constitute…

Large language model (LLM) inference has been a prevalent demand in daily life and industries. The large tensor sizes and computing complexities in LLMs have brought challenges to memory, computing, and databus. This paper proposes a…

Architectural simulation has become the critical bottleneck limiting design space exploration for high-performance computing systems. Modern GPUs and AI accelerators -- with hundreds to thousands of tightly-coupled components -- demand…

The Simplex tableau has been broadly used and investigated in the industry and academia. With the advent of the big data era, ever larger problems are posed to be solved in ever larger machines whose architecture type did not exist in the…

Production LLM serving must simultaneously deliver high throughput, low latency, and sufficient context capacity under non-stationary traffic and mixed request requirements. Data parallelism (DP) maximizes throughput by running independent…

In this paper, we consider a mixed-prompt scenario for a large language model (LLM) inference serving system that supports diverse applications with both short prompts and long prompts and heterogeneous SLOs for iteration time. To improve…

Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and…

Emerging workloads, such as graph processing and machine learning are approximate because of the scale of data involved and the stochastic nature of the underlying algorithms. These algorithms are often distributed over multiple machines…