6 accepted papers
In this paper, we investigate how to push the performance limits of serving Deep Neural Network (DNN) models on CPU-based servers. Specifically, we observe that while intra-operator parallelism across multiple threads is an effective way to reduce inference latency, it provides diminishing returns.…
New ML models are often derived from existing ones (e.g., through fine-tuning, quantization or distillation), forming an ecosystem where models are *related* to each other and can share structure or even parameter values. Managing such a large and evolving ecosystem of model derivatives is challengi…
Large language models (LLMs) are highly capable but also computationally expensive. Characterizing the _fundamental tradeoff_ between inference efficiency and model capabilities is thus important, but requires an efficiency metric that is comparable across models from different providers. Unfortuna…
The stunning qualitative improvement of text-to-image models has led to their widespread attention and adoption. However, we lack a comprehensive quantitative understanding of their capabilities and risks. To fill this gap, we introduce a new benchmark, Holistic Evaluation of Text-to-Image Models (H…
Many state-of-the-art ML results have been obtained by scaling up the number of parameters in existing models. However, parameters and activations for such large models often do not fit in the memory of a single accelerator device; this means that it is necessary to distribute training of large mode…
The rapid increase in sizes of state-of-the-art DNN models, and consequently the increase in the compute and memory requirements of model training, has led to the development of many execution schemes such as data parallelism, pipeline model parallelism, tensor (intra-layer) model parallelism, and v…