DCML - Inference Provider UI

Start your own workload and get proof that it was started in a secure environment

My Account

Select your inference provider account


    


    

      
Machine

      
Select GPU owner account and a machine to rent

      
      

        
        
      

      

        
        
      

    


    

      
Reservation

      
Reserve a machine or load an existing reservation

      

        

          
          
        

        

          

            
            

              
              
            

            

          

          
        

        

          
        

      

    


    

      
Provision

      
Specify Docker container image to run in the CVM and ports which it exposes

      

        
      

      

        

          
          
        

      


      

        Add custom port
        

          
          
          
        

        
        

      


      

        
        
      

      

      
    


    

      
Get proof

      
Get proof that your workload was indeed started in CVM

      

        
        

          (stub, to demonstrate that access info is shared securely)