onnxruntime
1d149f5a - Allow present_key to be empty when past_key is provided in Attention (#26303)

Commit
62 days ago
Allow present_key to be empty when past_key is provided in Attention (#26303) The original check enforces both the present_key and the past_key must be present. But with IO-binding there may be an issue: The past_key can be nullptr even when present_key is allocated. In reality, the kernel should just do the computation when it has the data, or when the output is requested. --------- Signed-off-by: Justin Chu <justinchuby@users.noreply.github.com>
Author
Parents
Loading