TensorRT-LLMs/docs/source
Robin Kobus 1bd84c6d8c
feat: Allow individual gatherContext for each additional output (#3374)
* refactor: Update ExecutorConfig to use AdditionalModelOutput type

- Changed function signatures and member variables across multiple files to replace std::optional<std::vector<std::string>> with std::optional<std::vector<executor::AdditionalModelOutput>> to include gatherContext flag for each additional output.
- Updated related serialization and deserialization methods to accommodate the new type.
- Adjusted tests to reflect the changes in the output handling structure.

This refactor enhances the flexibility and maintainability of the output configuration in the executor and batch manager components.

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

* refactor: Remove equality operator from TrtGptModelOptionalParams

- Deleted the operator== implementation from TrtGptModelOptionalParams to simplify the class.
- Updated the pybind11 bindings to remove the exposure of the equality operator to Python.

This change streamlines the class definition and reduces unnecessary complexity in the bindings.

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

* refactor: Enhance copyAdditionalOutputs to utilize AdditionalModelOutput

- Updated the copyAdditionalOutputs function to accept a vector of AdditionalModelOutput, allowing for the inclusion of the gatherContext flag.
- Adjusted the logic to handle context and non-context outputs separately, improving the output handling mechanism.
- Modified related unit tests to incorporate the new gatherContext parameter, ensuring comprehensive testing of the updated functionality.

This refactor improves the flexibility and clarity of output management in the batch processing workflow.

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

* refactor: Introduce findOutputTensor utility function for output tensor retrieval

- Added a new utility function, findOutputTensor, to encapsulate the logic for finding output tensors and checking their validity.
- Refactored copyAdditionalOutputs to utilize findOutputTensor, reducing code duplication and improving clarity.
- Enhanced error checking for additional context and generation output tensors.

This change streamlines the output tensor retrieval process, enhancing maintainability and readability in the batch processing workflow.

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

* refactor: Check final indices of additional output tensors and update tests

- Added checks to verify the final indices of additional output tensors for context and generation outputs.
- Updated unit tests to verify the changes.
  - Add lastTokenIds input tensor to test engines.
  - Logits output depends on gatherContextLogits parameter.
- Removed gatherContextOutputs parameter from the validate method in LlmRequest.
  - Context outputs do not depend on computeContextLogits parameter.

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

* fixup! refactor: Check final indices of additional output tensors and update tests

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

* fixup! refactor: Update ExecutorConfig to use AdditionalModelOutput type

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

* fixup! refactor: Remove equality operator from TrtGptModelOptionalParams

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

* docs: Update executor.md

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

* chore: Clean up includes

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

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
2025-04-12 17:00:36 +08:00
..
_templates Update TensorRT-LLM (#1725) 2024-06-04 20:26:32 +08:00
advanced feat: Allow individual gatherContext for each additional output (#3374) 2025-04-12 17:00:36 +08:00
architecture Update TensorRT-LLM (#2562) 2024-12-11 00:31:05 -08:00
blogs Update README and add benchmarking blog for DeepSeek-R1 (#3232) 2025-04-10 17:00:49 +08:00
commands doc: refactor trtllm-serve examples and doc (#3187) 2025-04-04 11:40:43 +08:00
dev-on-cloud doc: add doc ahout developent on cloud or runpod (#3194) 2025-04-02 18:10:56 +08:00
examples doc: refactor trtllm-serve examples and doc (#3187) 2025-04-04 11:40:43 +08:00
installation relax the limitation of setuptools (#2992) 2025-03-24 13:36:10 +08:00
llm-api Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
media L4 added to readme (#3301) 2025-04-06 19:09:28 +08:00
performance docs: Update perf-benchmarking doc on GPU configuration for consistent benchmarking. (#3458) 2025-04-11 17:21:27 +02:00
python-api Update TensorRT-LLM (#1492) 2024-04-24 14:44:22 +08:00
reference Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338) 2025-04-08 23:51:27 +08:00
torch feat: no-cache attention in PyTorch workflow (#3085) 2025-04-05 01:54:32 +08:00
conf.py Update (#2978) 2025-03-23 16:39:35 +08:00
helper.py doc: refactor trtllm-serve examples and doc (#3187) 2025-04-04 11:40:43 +08:00
index.rst doc: refactor trtllm-serve examples and doc (#3187) 2025-04-04 11:40:43 +08:00
key-features.md Update TensorRT-LLM (#2562) 2024-12-11 00:31:05 -08:00
overview.md Update (#2978) 2025-03-23 16:39:35 +08:00
quick-start-guide.md Update (#2978) 2025-03-23 16:39:35 +08:00
release-notes.md Update TensorRT-LLM (#2820) 2025-02-25 21:21:49 +08:00
torch.md Update TensorRT-LLM (#2820) 2025-02-25 21:21:49 +08:00