Skip to content
build

Implementation of tiled attention with bf16 and circular buffers which reduces memory requirements by 4x on longer context on gemma models. #6468

Sign in to view logs

Implementation of tiled attention with bf16 and circular buffers which reduces memory requirements by 4x on longer context on gemma models.

Implementation of tiled attention with bf16 and circular buffers which reduces memory requirements by 4x on longer context on gemma models. #6468

Triggered via pull request February 23, 2026 15:29
@copybara-servicecopybara-service[bot]
opened #839
test_864904207
Status Failure
Total duration 9m 51s
Artifacts –

build.yml

on: pull_request
bazel
1m 47s
bazel
Matrix: build
Fit to window
Zoom out
Zoom in

Annotations

4 errors and 1 warning
bazel
Process completed with exit code 1.
macos-latest (make) Release
Process completed with exit code 2.
ubuntu-latest (make) Release
Process completed with exit code 2.
windows-latest (windows) Release
Process completed with exit code 1.
bazel
Failed to restore: Cache service responded with 400