Multi model deployment#208

Draft

TosinSeg wants to merge 74 commits intodeepspeedai:mainfrom

TosinSeg:multi-model-deployment

Commits on Jun 19, 2023

Removing load balancing config
TosinSeg
committed

Commits on Jun 20, 2023

Commits on Jun 26, 2023

Commits on Jun 27, 2023

Commits on Jun 28, 2023

Commits on Jun 30, 2023

Commits on Jul 3, 2023

Commits on Jul 5, 2023

Commits on Jul 7, 2023

Refactoring Load balancer launch
TosinSeg
committed

Commits on Jul 10, 2023

Commits on Jul 11, 2023

Adding trust_remote_code support (#203)

authored

Commits on Jul 12, 2023

Commits on Jul 13, 2023

Merge branch 'multi-model-deployment' of github.com:TosinSeg/DeepSpeed-MII into multi-model-deployment
Tosin Segun
committed
Refactoring Load Balancer and request_proto
Tosin Segun
committed
Formatting
Tosin Segun
committed

Commits on Jul 14, 2023

Fixing the client
Tosin Segun
committed

Commits on Jul 21, 2023

Initial partial deployment commit
Tosin Segun
committed
More partial deploy updates
Tosin Segun
committed
Partial deploy started
Tosin Segun
committed

Commits on Jul 24, 2023

fixing add deploy api queries
Tosin Segun
committed
Support for empty deployment 'group'
Tosin Segun
committed
Support for empty deployment 'group'
Tosin Segun
committed

Commits on Jul 25, 2023

Partial Termination
Tosin Segun
committed
Refactoring
Tosin Segun
committed
formatting
Tosin Segun
committed
fixing bug for partial termination
Tosin Segun
committed
Removing comments
Tosin Segun
committed

Commits on Jul 26, 2023

Including GPU index map in score file
Tosin Segun
committed
Refactoring deployment
Tosin Segun
committed
Refactoring and formatting
Tosin Segun
committed

Commits on Jul 28, 2023

Refactoring
Tosin Segun
committed
Fixing Readme
Tosin Segun
committed
Refactoring GRPC
Tosin Segun
committed
Fixing LB process not terminating
Tosin Segun
committed

Commits on Jul 31, 2023

Adding multi_deployment and partial deploy/terminate unit tests
Tosin Segun
committed
Removing comments
Tosin Segun
committed

Commits on Aug 1, 2023

Fixing spelling issues
Tosin Segun
committed
Update mii/client.py

TosinSeg
and
mrwyattii
authored
Update mii/client.py

TosinSeg
and
mrwyattii
authored
Removing AML from addDeploy
Tosin Segun
committed

Commits on Aug 2, 2023

Refactoring MIIConfig and DeploymentConfig
Tosin Segun
committed

Commits on Aug 11, 2023

Partial deploy/termination example
Tosin Segun
committed