Posts

All the articles I've posted.

• How We Cut ML Inference Latency by 40% on Kubernetes

  31 May, 2023

  The architecture behind our async model serving platform at Instabase — async workers, RabbitMQ, multi-level caching, and sticky routing to cut inference time by 40%.

• GupShup: Summarizing Code-Switched Conversations

  6 Nov, 2021

  Our EMNLP 2021 paper on abstractive summarization of Hindi-English code-switched conversations — introducing the GupShup dataset.