Add chunked prefill with prefix KV cache reuse to Tunix Gemma 4.#1597
Open
copybara-service[bot] wants to merge 1 commit into
Open
Add chunked prefill with prefix KV cache reuse to Tunix Gemma 4.#1597copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
- Refactor attention into focused methods for KV projection, cache update with prefix concatenation, and mask construction. - Support sliding window (ring buffer) and linear cache layouts. - Handle PAD masking, KV sharing, and flash attention fallback. - Comprehensive tests for chunked prefill, decode, KV sharing, and PAD masking. PiperOrigin-RevId: 933189977
0ee18f7 to
5d7b355
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add chunked prefill with prefix KV cache reuse to Tunix Gemma 4.
cache update with prefix concatenation, and mask construction.
and PAD masking.