587 citations · 1.5k across the 25 of their papers we have counts for
30 papers
Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs
Yixuan Mei, Zikun Li, Zixuan Chen +5
The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-ge…
Bandwidth Cost of Locally Repairable Convertible Codes in the Global Merge Regime
Saransh Chopra, Shubhransh Singhvi, K. V. Rashmi
Recent studies have shown that distributed storage systems can achieve significant space savings by adapting redundancy levels to varying disk failure rates. This adaptation is per…
Tight Lower Bounds on the Bandwidth Cost of MDS Convertible Codes in the Split Regime
Shubhransh Singhvi, Saransh Chopra, K. V. Rashmi
Recent advances in erasure coding for distributed storage systems have demonstrated that adapting redundancy to varying disk failure rates can lead to substantial storage savings.…
On Low Field Size Constructions of Access-Optimal Convertible Codes
Saransh Chopra, Francisco Maturana, K. V. Rashmi
Most large-scale storage systems employ erasure coding to provide resilience against disk failures. Recent work has shown that tuning this redundancy to changes in disk failure rat…
Learning-Augmented Streaming Codes are Approximately Optimal for Variable-Size Messages
Michael Rudow, K. V. Rashmi
Real-time streaming communication requires a high quality of service despite contending with packet loss. Streaming codes are a class of codes best suited for this setting. A key c…
Bandwidth Cost of Code Conversions in the Split Regime
Francisco Maturana, K. V. Rashmi
Distributed storage systems must store large amounts of data over long periods of time. To avoid data loss due to device failures, an erasure code is used to encode dat…