TensorRT-LLMs/cpp/tensorrt_llm/batch_manager/utils
Robin Kobus 7c1565a2b6
[nvbugs/5274894] fix: Sort requests for functional correctness and performance (#4608)
* Revert "[nvbugs/5274894] fix: Moving finished context requests to generation (#4576)"

This reverts commit d39bcb6b40.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* fix: Sort requests for functional correctness and performance

- Moved sorting related logic to a dedicated function for better clarity and maintainability.
- Enhanced sorting logic to separate finished context requests from ongoing ones before sorting by Lora task ID.
- Updated function documentation to reflect the sorting behavior and its purpose.

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
2025-05-23 15:08:54 +02:00
..
debugUtils.cpp Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
debugUtils.h Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
inflightBatchingUtils.cpp [nvbugs/5274894] fix: Sort requests for functional correctness and performance (#4608) 2025-05-23 15:08:54 +02:00
inflightBatchingUtils.h [nvbugs/5274894] fix: Sort requests for functional correctness and performance (#4608) 2025-05-23 15:08:54 +02:00
logitsThread.cpp refactor: Introduce MpiTag enumeration and update MPI function signatures (#3893) 2025-05-04 13:24:29 +02:00
logitsThread.h refactor: Introduce MpiTag enumeration and update MPI function signatures (#3893) 2025-05-04 13:24:29 +02:00
staticThreadPool.cpp Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
staticThreadPool.h Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00