mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-22 03:35:00 +08:00
* fix: nvbugs/5075538: fix cross attention mask when decoder input len > 1 Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com> * remove waiver Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com> --------- Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| dev | ||
| qa | ||
| test-db | ||
| waives.txt | ||