Esha Choukseの肖像

Esha Choukse

Principal Researcher

Connect on LinkedIn

ニュース&特集

アワード | ACM SIGMICRO

Esha Choukse receives 2025 SIGMICRO Early Career Award 

Choukse was recognized for her foundational contributions to hardware memory compression and to sustainable and efficient datacenter systems.

Research Focus | September 23, 2024
Microsoft Research ブログ

Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. Time-series forecasting is a technique used to predict future values based on previously…

Research Focus April 15, 2024
Microsoft Research ブログ

In this issue: New research on appropriate reliance on generative AI; Power management opportunities for LLMs in the cloud; LLMLingua-2 improves task-agnostic prompt compression; Enhancing COMET to embrace under-resourced African languages:

An example of the generative LLM inference process and the two phases associated with it. The initial prompt is “Which is better, pizza or burger?” and it generates the word “Pizza”. The token generation phase generates the words/tokens: “is”, “better”, and “.”. The prompt phase has the following properties: (1) all input tokens are processed in parallel to generate the first output token, (2) compute intensive, and (3) is a smaller part of the end-to-end latency. The token phase is: (1) serialized, (2) memory intensive, and (3) tends to be the majority of the end-to-end latency.
Microsoft Research ブログ

| Esha Choukse, Chaojie Zhang, Íñigo Goiri, Aashaka Shah, Saeed Maleki, Rodrigo Fonseca, と Ricardo Bianchini

Expanded LLM use creates new demands on cloud GPU capacity. Splitwise presents an efficient solution by separating the two essential phases of LLM inference, achieving higher throughput within a limited power budget.