[Kernel] Pipe attn_logits_soft_cap through paged attention TPU kernels (#12482)

Browse Source

Signed-off-by: Fenghui Zhang <fhzhang@google.com>

...

This commit is contained in:

fenghuizhang

2025-01-28 14:36:44 -08:00

committed by GitHub

parent c386c43ca3

commit 80fcc3ed1c

2 changed files with 16 additions and 26 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

0

.buildkite/run-tpu-test.sh Normal file → Executable file