Runtime
==========

.. Here are files in the cpp/include/runtime
.. We manually add subsection to enable detailed description in the future
.. It is also doable to automatically generate this file and list all the modules in the conf.py
speculativeDecodingModule.h
___________________________

.. doxygenfile:: speculativeDecodingModule.h
   :project: TensorRT-LLM

generationOutput.h
__________________

.. doxygenfile:: generationOutput.h
   :project: TensorRT-LLM

cudaEvent.h
___________

.. doxygenfile:: cudaEvent.h
   :project: TensorRT-LLM

gptSession.h
____________

.. doxygenfile:: gptSession.h
   :project: TensorRT-LLM

loraCache.h
___________

.. doxygenfile:: loraCache.h
   :project: TensorRT-LLM

runtimeDefaults.h
_________________

.. doxygenfile:: runtimeDefaults.h
   :project: TensorRT-LLM

memoryCounters.h
________________

.. doxygenfile:: memoryCounters.h
   :project: TensorRT-LLM

eagleBuffers.h
______________

.. doxygenfile:: eagleBuffers.h
   :project: TensorRT-LLM

request.h
_________

.. doxygenfile:: request.h
   :project: TensorRT-LLM

bufferManager.h
_______________

.. doxygenfile:: bufferManager.h
   :project: TensorRT-LLM

gptDecoder.h
____________

.. doxygenfile:: gptDecoder.h
   :project: TensorRT-LLM

worldConfig.h
_____________

.. doxygenfile:: worldConfig.h
   :project: TensorRT-LLM

iBuffer.h
_________

.. doxygenfile:: iBuffer.h
   :project: TensorRT-LLM

ipcUtils.h
__________

.. doxygenfile:: ipcUtils.h
   :project: TensorRT-LLM

iStatefulGptDecoder.h
_____________________

.. doxygenfile:: iStatefulGptDecoder.h
   :project: TensorRT-LLM

promptTuningParams.h
____________________

.. doxygenfile:: promptTuningParams.h
   :project: TensorRT-LLM

medusaModule.h
______________

.. doxygenfile:: medusaModule.h
   :project: TensorRT-LLM

rawEngine.h
___________

.. doxygenfile:: rawEngine.h
   :project: TensorRT-LLM

samplingConfig.h
________________

.. doxygenfile:: samplingConfig.h
   :project: TensorRT-LLM

loraCachePageManagerConfig.h
____________________________

.. doxygenfile:: loraCachePageManagerConfig.h
   :project: TensorRT-LLM

generationInput.h
_________________

.. doxygenfile:: generationInput.h
   :project: TensorRT-LLM

speculativeDecodingMode.h
_________________________

.. doxygenfile:: speculativeDecodingMode.h
   :project: TensorRT-LLM

iGptDecoderBatched.h
____________________

.. doxygenfile:: iGptDecoderBatched.h
   :project: TensorRT-LLM

common.h
________

.. doxygenfile:: common.h
   :project: TensorRT-LLM

gptJsonConfig.h
_______________

.. doxygenfile:: gptJsonConfig.h
   :project: TensorRT-LLM

cudaStream.h
____________

.. doxygenfile:: cudaStream.h
   :project: TensorRT-LLM

lookaheadBuffers.h
__________________

.. doxygenfile:: lookaheadBuffers.h
   :project: TensorRT-LLM

tllmLogger.h
____________

.. doxygenfile:: tllmLogger.h
   :project: TensorRT-LLM

lookaheadModule.h
_________________

.. doxygenfile:: lookaheadModule.h
   :project: TensorRT-LLM

gptDecoderBatched.h
___________________

.. doxygenfile:: gptDecoderBatched.h
   :project: TensorRT-LLM

modelConfig.h
_____________

.. doxygenfile:: modelConfig.h
   :project: TensorRT-LLM

loraModule.h
____________

.. doxygenfile:: loraModule.h
   :project: TensorRT-LLM

iTensor.h
_________

.. doxygenfile:: iTensor.h
   :project: TensorRT-LLM

explicitDraftTokensBuffers.h
____________________________

.. doxygenfile:: explicitDraftTokensBuffers.h
   :project: TensorRT-LLM

decodingOutput.h
________________

.. doxygenfile:: decodingOutput.h
   :project: TensorRT-LLM

decodingInput.h
_______________

.. doxygenfile:: decodingInput.h
   :project: TensorRT-LLM