Vikram Sharma Mailthody

Dr. Vikram Sharma Mailthody is part of NVIDIA Research and a co-architect of NVIDIA Dynamo. His work focuses on solving foundational systems-level challenges in emerging data center workloads, with an emphasis on scalable GPU memory and storage system architectures.

Posts by Vikram Sharma Mailthody

AI Platforms/Deployment Sep 30, 2026

Expanding AI Storage Access with NVIDIA cuObject and the NVIDIA SCADA Server SDK

AI infrastructure engineers, storage developers, and cloud service providers need fast and secure access to high-capacity file and object storage to support AI... 5 MIN READ

Developer Tools & Techniques Aug 25, 2026

Restore LLM Inference Capacity in Seconds with Shadow Engine Recovery in NVIDIA Dynamo

When an LLM engine process fails, the standard recovery path involves a cold restart. This requires loading weights into HBM from storage, compiling kernels,... 13 MIN READ

Agentic AI / Generative AI May 29, 2026

DynoSim: Simulating the Pareto Frontier

Modern LLM serving is hard to tune because each deployment is a stack of interacting choices: model backend, tensor-parallel shape, prefill/decode split, worker... 12 MIN READ

NVIDIA Dynamo Snapshot: Fast Startup for Inference Workloads on Kubernetes

The cold-start problem In production inference deployments, demand fluctuates over time, requiring inference replicas to scale elastically. However,... 15 MIN READ

Data Center / Cloud May 20, 2025

NVIDIA Dynamo Adds GPU Autoscaling, Kubernetes Automation, and Networking Optimizations

At NVIDIA GTC 2025, we announced NVIDIA Dynamo, a high-throughput, low-latency open-source inference serving framework for deploying generative AI and reasoning... 7 MIN READ