Memory restrictions and limited parallelism for model prediction #196
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
…ith a platform-limited version based on Default Dispatcher, ResourcesDispatcher prevents unlimited creation of AllocatorContext (this behavior caused OOM).
…ting avoiding boxing operations
…earing in ndarray-core
# Conflicts: # ndarray/ndarray-core/src/jvmMain/kotlin/io/kinference/ndarray/arrays/memory/ArrayDispatcher.kt # ndarray/ndarray-core/src/jvmMain/kotlin/io/kinference/ndarray/arrays/memory/MemoryLimiter.kt # ndarray/ndarray-core/src/jvmMain/kotlin/io/kinference/ndarray/arrays/memory/ModelArrayStorage.kt
…lt limiter for the 0.3 of the max heap size, NoAllocator limiter when user doesn't want to reuse any allocated arrays.
…ead of KIEngine. Standard close() function always clears model cache.
… commonMain and move to jvm specific ConcurrentLinkedQueue without expect/actual.
cupertank
requested changes
Jul 26, 2024
utils/utils-common/src/commonMain/kotlin/io/kinference/utils/ResourcesDispatcher.kt
Outdated
Show resolved
Hide resolved
…ate parameter names: default limiter is now NoAllocator, better naming for deducting memory and for size in bytes for arrays.
…er logic: added MemoryLimiter to ArrayStorage constructor for better memory control. Removed isNewlyCreated flag from ArrayContainer and streamlined getArrayContainers logic in AllocatorContext.
cupertank
approved these changes
Jul 31, 2024
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Outdated suggestions cannot be applied.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.
No description provided.