From c040bbe50f2b98830e0ba2bd0be72fd93ce55bb9 Mon Sep 17 00:00:00 2001 From: Smoothengineer <160827599+Smoothengineer@users.noreply.github.com> Date: Mon, 14 Oct 2024 02:34:52 +0530 Subject: [PATCH] [DOC] Improved wording and clarity in README.md Signed-off-by: Smoothengineer <160827599+Smoothengineer@users.noreply.github.com> --- README.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index eaf275c2..20cf44f5 100644 --- a/README.md +++ b/README.md @@ -38,12 +38,12 @@ Mosec is a high-performance and flexible model serving framework for building ML model-enabled backend and microservices. It bridges the gap between any machine learning models you just trained and the efficient online service API. -- **Highly performant**: web layer and task coordination built with Rust 🦀, which offers blazing speed in addition to efficient CPU utilization powered by async I/O -- **Ease of use**: user interface purely in Python 🐍, by which users can serve their models in an ML framework-agnostic manner using the same code as they do for offline testing -- **Dynamic batching**: aggregate requests from different users for batched inference and distribute results back -- **Pipelined stages**: spawn multiple processes for pipelined stages to handle CPU/GPU/IO mixed workloads -- **Cloud friendly**: designed to run in the cloud, with the model warmup, graceful shutdown, and Prometheus monitoring metrics, easily managed by Kubernetes or any container orchestration systems -- **Do one thing well**: focus on the online serving part, users can pay attention to the model optimization and business logic +- **Highly performant**: Web layer and task coordination built with Rust 🦀, which offers blazing speed in addition to efficient CPU utilization powered by async I/O +- **Ease of use**: The user interface is purely in Python 🐍, by which users can serve their models in an ML framework-agnostic manner using the same code as they do for offline testing +- **Dynamic batching**: Aggregates requests from different users for batched inference and distribute results back +- **Pipelined stages**: Spawns multiple processes for pipelined stages to handle CPU/GPU/IO mixed workloads +- **Cloud friendly**: Designed to run in the cloud, with the model warmup, graceful shutdown, and Prometheus monitoring metrics, easily managed by Kubernetes or any container orchestration systems +- **Do one thing well**: Focus on the online serving part, users can pay attention to the model optimization and business logic ## Installation