Skip to content

Fix: Resolve KV Cache OOM & Logit Extraction Memory Spikes#678

Open
prince-shakyaa wants to merge 4 commits into
google-deepmind:mainfrom
prince-shakyaa:fix-memory-oom-v3
Open

Fix: Resolve KV Cache OOM & Logit Extraction Memory Spikes#678
prince-shakyaa wants to merge 4 commits into
google-deepmind:mainfrom
prince-shakyaa:fix-memory-oom-v3

Merge remote-tracking branch 'upstream/main' into pr-678

888713c
Select commit
Loading
Failed to load commit list.
Google CLA / cla/google succeeded Jul 6, 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:

888713c Author: @prince-shakyaa <psp******005​@gmail.com>

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