Rammer: Enabling Holistic Deep Learning Compiler Optimizations with rTasks

By Lingxiao Ma, Zhiqiang Xie, Zhi Yang, Jilong Xue, Youshan Miao, Wei Cui, Wenxiang Hu, Fan Yang, Lintao Zhang, Lidong Zhou. 2020

200 citations recorded by the source corpus.

Subfields: ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In ML Systems & Hardware

1. Joseph E. Gonzalez
2. Ion Stoica
3. Lianmin Zheng

Citations in the corpus

• Efficient Memory Management for Large Language Model Serving with PagedAttention (2023, methodology): “These systems utilize GPU kernel optimizations [1, 29, 31, 56], advanced batching mechanisms [14, 60], model parallelism [1, 41, 60], and parameter sharing [64] for efficient serving.”
• Orca: A Distributed Serving System for Transformer-Based Generative Models (2022, background): “Although this fusion makes the thread blocks within a kernel have different characteristics and lifetimes (which is often discouraged by CUDA programming practice) because they process tensors of different shapes, we find this fusion to be beneficial by improving GPU utilization and reducing the ker”
• This paper is included in the Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation. (unknown): “Compiler techniques have been introduced to optimize the execution of DL models [13,24,34,51,52,54,62].”