openvino_genai.RawPerfMetrics#

class openvino_genai.RawPerfMetrics#

Bases: pybind11_object

Structure with raw performance metrics for each generation before any statistics are calculated.

Parameters:

generate_durations (List[MicroSeconds]) – Durations for each generate call in microseconds.
tokenization_durations (List[MicroSeconds]) – Durations for the tokenization process in microseconds.
detokenization_durations (List[MicroSeconds]) – Durations for the detokenization process in microseconds.
m_times_to_first_token (List[MicroSeconds]) – Times to the first token for each call in microseconds.
m_new_token_times (List[MilliSeconds]) – Timestamps of generation every token or batch of tokens in milliseconds.
m_batch_sizes (List[int]) – Batch sizes for each generate call.
m_durations (List[MicroSeconds]) – Total durations for each generate call in microseconds.
num_generated_tokens (int) – Total number of tokens generated.
num_input_tokens (int) – Total number of tokens in the input prompt.

__init__(self: openvino_genai.py_openvino_genai.RawPerfMetrics) → None#

Methods

`__delattr__`(name, /)	Implement delattr(self, name).
`__dir__`()	Default dir() implementation.
`__eq__`(value, /)	Return self==value.
`__format__`(format_spec, /)	Default object formatter.
`__ge__`(value, /)	Return self>=value.
`__getattribute__`(name, /)	Return getattr(self, name).
`__gt__`(value, /)	Return self>value.
`__hash__`()	Return hash(self).
`__init__`(self)
`__init_subclass__`	This method is called when a class is subclassed.
`__le__`(value, /)	Return self<=value.
`__lt__`(value, /)	Return self<value.
`__ne__`(value, /)	Return self!=value.
`__new__`(**kwargs)
`__reduce__`()	Helper for pickle.
`__reduce_ex__`(protocol, /)	Helper for pickle.
`__repr__`()	Return repr(self).
`__setattr__`(name, value, /)	Implement setattr(self, name, value).
`__sizeof__`()	Size of object in memory, in bytes.
`__str__`()	Return str(self).
`__subclasshook__`	Abstract classes can override this to customize issubclass().

Attributes

`detokenization_durations`
`generate_durations`
`m_batch_sizes`
`m_durations`
`m_new_token_times`
`m_times_to_first_token`
`tokenization_durations`

__class__#: alias of pybind11_type

__delattr__(name, /)#: Implement delattr(self, name).

__dir__()#: Default dir() implementation.

__eq__(value, /)#: Return self==value.

__format__(format_spec, /)#: Default object formatter.

__ge__(value, /)#: Return self>=value.

__getattribute__(name, /)#: Return getattr(self, name).

__gt__(value, /)#: Return self>value.

__hash__()#: Return hash(self).

__init__(self: openvino_genai.py_openvino_genai.RawPerfMetrics) → None#

__init_subclass__()#

This method is called when a class is subclassed.

The default implementation does nothing. It may be overridden to extend subclasses.

__le__(value, /)#: Return self<=value.

__lt__(value, /)#: Return self<value.

__ne__(value, /)#: Return self!=value.

__new__(**kwargs)#

__reduce__()#: Helper for pickle.

__reduce_ex__(protocol, /)#: Helper for pickle.

__repr__()#: Return repr(self).

__setattr__(name, value, /)#: Implement setattr(self, name, value).

__sizeof__()#: Size of object in memory, in bytes.

__str__()#: Return str(self).

__subclasshook__()#

Abstract classes can override this to customize issubclass().

This is invoked early on by abc.ABCMeta.__subclasscheck__(). It should return True, False or NotImplemented. If it returns NotImplemented, the normal algorithm is used. Otherwise, it overrides the normal algorithm (and the outcome is cached).

property detokenization_durations#

property generate_durations#

property m_batch_sizes#

property m_durations#

property m_new_token_times#

property m_times_to_first_token#

property tokenization_durations#