SlashML provides a platform that packages Streamlit, Gradio, and Dash machine‑learning web apps into ready‑to‑deploy Docker containers with a unified UI. Users point the service to a Hugging Face model repository and SlashML handles provisioning, launching, and public endpoint creation while offering real‑time cost and performance monitoring. The solution lets data scientists and ML engineers focus on model development instead of infrastructure configuration.
Funding
Funding not disclosed
Founders
Product
Problem
Machine learning developers often spend excessive time configuring environments, managing dependencies, and setting up infrastructure to host interactive apps such as Streamlit, Gradio, or Dash. This complexity hampers rapid iteration and makes cost monitoring difficult, especially when using shared or cloud GPUs.
Solution
SlashML offers a platform that packages ML web apps into ready-to-deploy Docker containers with a unified web UI. Users simply point the system to a model repository on Hugging Face, and SlashML handles the provisioning of either its own GPUs or the user’s hardware. The service automatically launches the app, provides a public endpoint, and integrates real‑time cost and performance observability. By abstracting configuration and infrastructure concerns, SlashML enables developers to focus on model development and user experience while maintaining visibility into resource usage.
Target Audience
Primary customers are data scientists, ML engineers, and AI product teams that need to quickly expose interactive model demos or internal tools without managing low‑level infrastructure.
Features
- One‑click deployment of Streamlit, Gradio, and Dash applications via pre‑built Docker images
- UI dashboard for launching, monitoring, and scaling apps without manual CLI commands
- Automatic cost and resource usage tracking tied to each running process
- Support for both SlashML‑hosted GPUs and user‑provided compute resources
- Simple integration with Hugging Face model repositories for model loading
- Built‑in process monitoring that captures PID, port, and health metrics