mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
- 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> |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| decodingConfigTest.cpp | ||
| dynamicBatchTunerTest.cpp | ||
| executorConfigTest.cpp | ||
| executorTestSmall.cpp | ||
| executorTestSmallArbitraryOutputTensors.cpp | ||
| intervalSetTest.cpp | ||
| kvCacheConfigTest.cpp | ||
| loraConfigTest.cpp | ||
| requestTest.cpp | ||
| requestWithIdTest.cpp | ||
| responseTest.cpp | ||
| samplingConfigTest.cpp | ||
| serializeUtilsTest.cpp | ||
| tensorTest.cpp | ||
| ucxCommTest.cpp | ||