vllm/model_executor/models/gemma4.py · 9a234c7adca95bbdf2c1dc410c5617d421ac3c11 · OpenDAS / vllm_cscc

[Gemma4] Enable Fast Prefill Optimization (#38879) · 6f3dc4d0

Lucas Wilkinson authored Apr 06, 2026


Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
(cherry picked from commit 47e60509)
(cherry picked from commit fc29ef13a0dff7c4fa14590655a160f20fb7124d)

6f3dc4d0

gemma4.py 60.6 KB

Replace gemma4.py