alekhjindal's Stars
microsoft/Peregrine
Peregrine is a workload optimization platform for cloud query engines. The goal of Peregrine is three-fold: 1. make it easier to ingest and analyze query workload telemetry into a common engine-agnostic representation, 2. help developers to quickly build workload optimization applications to reduce overall costs and improve operational efficiency, and 3. providing better experience to the customers in the form of workload insights, actionable recommendations, and self-tuning capabilities.
RunLLM/aqueduct
Aqueduct is no longer being maintained. Aqueduct allows you to run LLM and ML workloads on any cloud infrastructure.
microsoft/hummingbird
Hummingbird compiles trained ML models into tensor computation for faster inference.