Search Results for author:
Found 11 papers, 2 papers with code
FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping
In this work, we observed the saturation of computationally expensive feed-forward blocks of LLM layers and proposed FFN-SkipLLM, which is a novel fine-grained skip strategy of autoregressive LLMs.
Accelerating Distributed Deep Learning using Lossless Homomorphic Compression
As deep neural networks (DNNs) grow in complexity and size, the resultant increase in communication overhead during distributed training has become a significant bottleneck, challenging the scalability of distributed training systems.
On a Foundation Model for Operating Systems
This paper lays down the research agenda for a domain-specific foundation model for operating systems (OSes).
MOSEL: Inference Serving Using Dynamic Modality Selection
Rapid advancements over the years have helped machine learning models reach previously hard-to-achieve goals, sometimes even exceeding human capabilities.
CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters
We present CASSINI, a network-aware job scheduler for machine learning (ML) clusters.
Auxo: Efficient Federated Learning via Scalable Client Clustering
In this paper, we explore an additional layer of complexity to mitigate such heterogeneity by grouping clients with statistically similar data distributions (cohorts).
Impact of RoCE Congestion Control Policies on Distributed Training of DNNs
Our results indicate that previously proposed RoCE congestion control schemes have little impact on the end-to-end performance of training workloads, motivating the necessity of designing an optimized, yet low-overhead, congestion control scheme based on the characteristics of distributed training platforms and workloads.
Multi-agent Databases via Independent Learning
Thus, the paper attempts to address the question "Is it possible to design a database consisting of various learned components that cooperatively work to improve end-to-end query latency?".
Doing More by Doing Less: How Structured Partial Backpropagation Improves Deep Learning Clusters
This simultaneously reduces network bandwidth, compute utilization, and memory footprint while preserving model quality.
Accelerating Deep Learning Inference via Learned Caches
We present the design of GATI, an end-to-end prediction serving system that incorporates learned caches for low-latency DNN inference.
Accelerating Deep Learning Inference via Freezing
In this work, we observe that caching intermediate layer outputs can help us avoid running all the layers of a DNN for a sizeable fraction of inference requests.
