API Reference
-------------

.. autoclass:: tensorrt_llm.llmapi.LLM
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.CompletionOutput
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.RequestOutput
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.GuidedDecodingParams
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.SamplingParams
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.DisaggregatedParams
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.KvCacheConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.KvCacheRetentionConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.LookaheadDecodingConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.MedusaDecodingConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.EagleDecodingConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.MTPDecodingConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.SchedulerConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.CapacitySchedulerPolicy
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.BuildConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.QuantConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.QuantAlgo
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.CalibConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.BuildCacheConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.RequestError
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.MpiCommSession
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.ExtendedRuntimePerfKnobConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.BatchingType
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.ContextChunkingPolicy
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.DynamicBatchConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance:
.. autoclass:: tensorrt_llm.llmapi.CacheTransceiverConfig
    :members:
    :undoc-members:
    :special-members: __init__
    :show-inheritance: