Skip to content

Author

Vikram Sharma Mailthody

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Koi: Evidence-Guided, Self-Calibrating Planning for Multi-Cloud, Heterogeneous LLM Inference Fleets

Deploying a large language model (LLM) requires choosing the right accelerator, parallelization strategy, engine configuration, and replica count amongst ~140 other variables across clouds, regions, and markets. These decisions are intertwined, and the best cluster-wide plan continually changes as jobs contend for shar...

Mankeerat Sidhu, Gang-Muk Lim, Hetarth Chopra et al. · 0 citations
Sep 2026

Fast Recovery for LLM Serving via Decoupled Device Memory Lifetime in Dynamo

This work argues that the dominant cost is loss of ready serving capacity, not request progress, so recovery should preserve initialized engine state rather than reconstruct it, and presents fast recovery for Dynamo based on this principle.

Schwinn Saereesitthipitak, Mohammed H. Abdulwahhab, Hannah Zhang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.