Qualcomm AI Engine Direct - Optimize QNN embedding op for llama#6725

Closed

shewu-quic wants to merge 2 commits intopytorch:mainfrom

CodeLinaro:dev1/hutton/optimize_qnn_embedding_op_in_llama

Commits on Nov 10, 2024

Qualcomm AI Engine Direct - Optimize QNN embedding op for llama
shewu-quic
committed

Commits on Nov 11, 2024

set default value for use_int32_token
shewu-quic
committed