DeployPad Changelog

DeployPad Engineering
,
1

Version 1.0 -Released

Release Summary

Initial public release of DeployPad, focused on simplified model deployment, optimized inference, and foundational billing and notification capabilities.

Features

Feature Description
One-click model launch Deploy models with a single action, without manual infrastructure setup
Pre-optimized models Models are deployed with DeployPad-managed optimization and tuning
Custom batching Low-latency, high-throughput inference with custom batching strategies
GPU support Optimized inference on H100, H200, L40S, RTX Pro 6000
Account top-up Manual balance top-up for usage billing
Email notifications System and account notifications via email
Billing notifications Usage and billing alerts

Supported Models

Model
arcee-ai / Trinity-Mini
IQuestLab / IQuest-Coder-V1-40B
2

Version 1.1 (Coming Soon)

Planned Improvements

The following features are currently under development and will be included in the next release.

Features (Planned)

Feature Description
Automatic account top-up Maintain service continuity with automated balance replenishment
Fast deployments End-to-end deployment in under 3 minutes
Location-based GPU availability View and select GPU availability by region

Models (Planned)

Model
meituan-longcat / LongCat-Flash-Lite
miromind-ai / MiroThinker-v1.5-30B
1 Like