tidy: Clean up various adapter/puller logic #33
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Motivation While working on adding built-in adapter support for torchserve, I noticed various things to be added/tidied in the adapter logic. Note that there's still a lot of simplification that could be done - de-duplicating/unifying common logic between the different adapters. Modifications - Move logic for resolving gRPC endpoint from ServingRuntime endpoint into a utility function - Change adapterConfig.RootModelDir to reference the subdir containing the _adapted_ model files/dirs - Create the adapter model subdir when the adapter is first created - Change the initial gRPC connection to the model server(s) to be non-blocking and remove connection test from that context - the runtimeStatus func will be called subsequently to determine when the connection/server is ready - Add logic to RuntimeStatus impls and puller to clean up local storage when called (per the SPI contract) - Add/clean-up some logging, particularly related to adaptModelLayout logic - Inline some if assignments :) Result Signed-off-by: Nick Hill <[email protected]>
Signed-off-by: Nick Hill <[email protected]>
chinhuang007
approved these changes
Sep 20, 2022
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: chinhuang007, njhill The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
|
/lgtm |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Motivation
While working on adding built-in adapter support for torchserve, I noticed various things to be added/tidied in the adapter logic.
Note that there's still a lot of simplification that could be done - in particular de-duplication and unification of common logic between the different adapters.
Modifications
adapterConfig.RootModelDirto reference the subdir containing the adapted model files/dirsruntimeStatusfunc will be called subsequently to determine when the connection/server is readyRuntimeStatusimpls and puller to clean up local storage when called (per the SPI contract)adaptModelLayoutlogic