5 papers
LGNNIC: Acceleration of Large-Scale GNN Training using SmartNICs
Liad Gerstman, Aditya Dhakal, Dejan Milojicic +1
Graph Neural Networks (GNNs) are widely used across domains such as natural sciences, social network analysis, chip design, and recommendation systems. However, as graph sizes grow…
Energy-Aware Scheduling for Serverless LLM Serving on Shared GPUs
Tianyu Wang, Gourav Rattihalli, Aditya Dhakal +2
As LLM inference becomes a major cloud workload, its growing energy footprint makes cluster-wide energy optimization increasingly important. Serverless LLM serving helps platforms…
Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding
Tianyu Wang, Gourav Rattihalli, Aditya Dhakal +4
Dynamic sparse attention (DSA) accelerates long-context LLM decoding by attending to only the top-K KV blocks relevant to each query, but it introduces a serialized selection-to-at…
ObjectCache: Layerwise Object-Storage Retrieval for KV Cache Reuse
Yu Zhu, Aditya Dhakal, Yunming Xiao +2
Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests that share a prefix (i.e., the…
An RDMA-First Object Storage System with SmartNIC Offload
Yu Zhu, Aditya Dhakal, Pedro Bruel +4
AI training and inference impose sustained, fine-grain I/O that stresses host-mediated, TCP-based storage paths. Motivated by kernel-bypass networking and user-space storage stacks…