Skip to content

Reduce local KV memory in BF16 Flash attention - #1020

Open
Mikyx-1 wants to merge 2 commits into
google:devfrom
Mikyx-1:fix/local-kv-rings-dev
Open

Reduce local KV memory in BF16 Flash attention#1020
Mikyx-1 wants to merge 2 commits into
google:devfrom
Mikyx-1:fix/local-kv-rings-dev

Use compact KV storage throughout Flash attention

8b8e56a
Select commit
Loading
Failed to load commit list.
Google CLA / cla/google succeeded Sep 8, 2026 in 7s

✅ All contributors are covered under a CLA with Google

See https://cla.developers.google.com/ for more info about Google's Contributor License Agreement (CLA).

ℹ️ Googlers: Go here to view more details and manage scans for this pull request.

Details

The following contributors were found for this pull request:

✅ 8b8e56a Author: @Mikyx-1 <leh*******t2k​@gmail.com>

(Only the first commit for a unique contributor is listed.)

View more details on Google CLA