Refactor CacheManager, Working Async #591
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
Splits the CacheManager into a CacheEngine interface along with a manager to manage a global cache. This then modifies the CacheEngine to also include a few additional pieces. It has a way to create a cache key before needing to store it which is used by the async and streaming sections. There is also some tentative features for multiTenant online caches. It also modifies the InferenceRequestHandler's handling of async. Before, it wasn't actually asynchronous as it had to wait for the result to send the response. This sends the response before the computation is started. Additionally, this PR also contains some changes adding a config to the Workflow system.
frankfliu
reviewed
Apr 2, 2023
| */ | ||
| public static CacheManager getInstance() { | ||
| public static CacheEngine getInstance() { |
There was a problem hiding this comment.
Suggested change
| public static CacheEngine getInstance() { | |
| public static CacheEngine getCacheEngine() { |
| */ | ||
| public static void setCacheManager(CacheManager instance) { | ||
| public static void setCacheManager(CacheEngine instance) { |
There was a problem hiding this comment.
Suggested change
| public static void setCacheManager(CacheEngine instance) { | |
| public static void setCacheEngine(CacheEngine instance) { |
frankfliu
approved these changes
Apr 3, 2023
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Outdated suggestions cannot be applied.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.
Splits the CacheManager into a CacheEngine interface along with a manager to manage a global cache. This then modifies the CacheEngine to also include a few additional pieces. It has a way to create a cache key before needing to store it which is used by the async and streaming sections. There is also some tentative features for multiTenant online caches.
It also modifies the InferenceRequestHandler's handling of async. Before, it wasn't actually asynchronous as it had to wait for the result to send the response. This sends the response before the computation is started.
Additionally, this PR also contains some changes adding a config to the Workflow system.