mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
b5bc0a9fcd
- Updated the first dimension of additional output tensors to match mMaxNewTokens. - Copy output of last context token to generation outputs. - Adjusted the expected output size calculations in unit tests to reflect the correct maximum output length. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| batch_manager | ||
| common | ||
| cutlass_extensions/include/cutlass_extensions | ||
| executor | ||
| executor_worker | ||
| kernels | ||
| layers | ||
| plugins | ||
| pybind | ||
| runtime | ||
| thop | ||
| CMakeLists.txt | ||