From 9544573cec51dab1370b874c576f219549d5b9f3 Mon Sep 17 00:00:00 2001
From: Nripesh Niketan <86844847+NripeshN@users.noreply.github.com>
Date: Thu, 16 Nov 2023 15:55:10 +0400
Subject: [PATCH] feat: Add Inferless service definition to orchestration (#14)

* Add Inferless service definition to orchestration

* Refactored inferless.yaml for improved model
deployment and cost optimization
---
 orchestration/inferless.yaml | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
 create mode 100644 orchestration/inferless.yaml

diff --git a/orchestration/inferless.yaml b/orchestration/inferless.yaml
new file mode 100644
index 0000000..2c9627a
--- /dev/null
+++ b/orchestration/inferless.yaml
@@ -0,0 +1,18 @@
+inferless:
+  name: "Inferless"
+
+  image_url: https://assets-global.website-files.com/640eae2485ab876a9c047cb2/640eb15f24ccc7295ffa2f76_Component%20logo.svg
+
+  tags: 
+    - model-endpoint
+    - orchestration
+
+  url: https://www.inferless.com/
+
+  description: "Inferless offers a serverless GPU solution for scaling machine learning inference without the complexities of server management. It enables rapid model deployment and customization, focusing on reducing infrastructure costs and enhancing user flexibility. Inferless streamlines the deployment process, handling scalability and operational challenges."
+
+  features:
+    - "Serverless GPU Inference: Deploy ML models seamlessly with serverless GPUs, offering ease of scaling and deployment."
+    - "Infrastructure Cost Optimization: Save up to 80% on infrastructure costs with transparent billing and efficient resource utilization."
+    - "Seamless Autoscaling: In-house built load balancer for efficient service scaling with minimal overhead."
+    - "GPU Virtualization: Facilitates the deployment of multiple models on a single GPU instance, catering to customized requirements."