[Runtime] Use preferred host memory (pinned memory) in KV cache #17036
Conversation
This file contains hidden or 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
This PR updates the PagedKVCache with the pinned memory support, which can reduce the copy overhead between CPU and GPU. This PR also bumps FlashInfer version, which now supports * specifying kernels to build via cmake, * pinned memory as host memory. We also update CMakeLists.txt and config.cmake to include the FlashInfer compile options. Prior to this PR, the kernels being built is hardcoded in FlashInfer header files.
Member
|
@tvm-bot rerun |
tqchen
approved these changes
May 29, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
This PR updates the PagedKVCache with the pinned memory support, which can reduce the copy overhead between CPU and GPU.
This PR also bumps FlashInfer version, which now supports
We also update CMakeLists.txt and config.cmake to include the FlashInfer compile options. Prior to this PR, the kernels being built is hardcoded in FlashInfer header files.