feat: decouple float and int workspace buffer #442
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
yzh119
added a commit
that referenced
this pull request
Aug 13, 2024
🤖 I have created a release *beep* *boop* --- ## [0.1.5](v0.1.4...v0.1.5) (2024-08-13) ### Bugfix * Fix PagedPrefill python api and some typos ([#441](#441)) ([3fff008](3fff008)) * fix prefill kernels' lse result for empty kv-cache ([#440](#440)) ([6ac28f4](6ac28f4)) ### Features * decouple float and int workspace buffer ([#442](#442)) ([a7ee566](a7ee566)) ### Performance Improvements * faster fp8->fp16 dequantization for pre sm_90 arch ([#439](#439)) ([c93f647](c93f647)) ### Acknowledgement We thank contributions and feedbacks from the community: [@comaniac](https://github.com/comaniac), [@hnyls2002](https://github.com/hnyls2002), [@jianfei-wangg](https://github.com/jianfei-wangg), [@Yard1](https://github.com/Yard1). --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Zihao Ye <expye@outlook.com>
# for free
to join this conversation on GitHub.
Already have an account?
# 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Outdated suggestions cannot be applied.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.
Before this PR, flashinfer coupled float and int buffers in a single workspace buffer, and different wrappers cannot share the same buffers.
This PR decouples float and int workspace buffer. The float workspace buffer (large) can be shared in multiple wrappers, and the int buffer (small) is unique for each wrapper. This PR can save GPU memory when multiple wrappers are created (decode, prefill paged, prefill ragged) or cascade inference.