Skip to content

perf(qwen3-next): nested scan over hybrid attention with per-layer remat - #4964

Open
NuojCheng wants to merge 8 commits into
mainfrom
chengnuojin-bharatgen-scan
Open

perf(qwen3-next): nested scan over hybrid attention with per-layer remat#4964
NuojCheng wants to merge 8 commits into
mainfrom
chengnuojin-bharatgen-scan

Drop full_attention_layer_offset

ceedbea
Select commit
Loading
Failed to load commit list.
Google CLA / cla/google succeeded Aug 24, 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:

ceedbea Author: @NuojCheng <che******in​@google.com>

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