llama: fix qwen4exp (#29751)
* llama: fix qwen4exp * qwen4exp: keep kq_mask input the same shape
A
Aman Gupta committed
66e0c17ee1741fef493312e17fe60a5d2cf5f7d5
Parent: 7677678
Committed by GitHub <noreply@github.com>
on 10/1/2026, 11:13:27 AM