Class | Description |
---|---|
Allocator |
Custom Allocator object for providing custom functions for allocator.
|
BackendConfig |
Structure to hold backend configuration for setting 'ServerOptions'.
|
CUDAMemoryPoolByteSize |
Structure to hold CUDA memory pool byte size for setting 'ServerOptions'.
|
GenericInferRequest |
Object that describes an inflight inference request.
|
GenericInferResult |
An interface for InferResult object to interpret the response to an
inference request.
|
GenericTritonServer |
Object that encapsulates in-process C API functionalities.
|
HostPolicy |
Structure to hold host policy for setting 'ServerOptions'.
|
InferOptions |
Structure to hold options for Inference Request.
|
LoggingOptions |
Structure to hold logging options for setting 'ServerOptions'.
|
MetricsOptions |
Structure to hold metrics options for setting 'ServerOptions'.
|
ModelLoadGPULimit |
Structure to hold GPU limit of model loading for setting 'ServerOptions'.
|
NewModelRepo |
Structure to hold the full path to the model repository to be registered and
the mapping from the original model name to the overridden one.
|
OutputBufferReleaseFn_t | |
RateLimitResource |
Structure to hold rate limit resource for setting 'ServerOptions'.
|
RepositoryIndex |
Structure to hold repository index for 'ModelIndex' function.
|
ResponseAllocatorAllocFn_t |
Custom Response Allocator Callback function signatures.
|
ResponseAllocatorStartFn_t | |
ServerOptions |
Server options that are used to initialize Triton Server.
|
StringSet | |
StringSet.Iterator | |
StringVector | |
StringVector.Iterator | |
Tensor |
Structure to hold information of a tensor.
|
Trace |
Structure to hold global trace setting for 'ServerOptions' and
model-specific trace setting for 'InferOptions'.
|
TritonException |
Copyright © 2024. All rights reserved.