MCPcopy Create free account

hub / github.com/OpenNMT/CTranslate2 / functions

Functions2,508 in github.com/OpenNMT/CTranslate2

↓ 341 callersMethodsize
src/vocabulary.cc:77
↓ 274 callersMethoddim
include/ctranslate2/storage_view.h:124
↓ 220 callersMethoddtype
Actual storage type.
include/ctranslate2/storage_view.h:99
↓ 215 callersMethoddevice
src/profiler.cc:64
↓ 209 callersMethodset_linear
(self, spec, module, quant_type=common_spec.Quantization.CT2)
python/ctranslate2/converters/transformers.py:237
↓ 206 callersMethodto
src/storage_view.cc:90
↓ 180 callersFunctioncreate
include/nlohmann/json.hpp:19551
↓ 166 callersMethodjoin
src/thread_pool.cc:105
↓ 162 callersMethodend
return iterator end (needed for range-based for)
include/nlohmann/json.hpp:5261
↓ 146 callersMethodbegin
return iterator begin (needed for range-based for)
include/nlohmann/json.hpp:5255
↓ 144 callersFunctionexpect_storage_eq
tests/test_utils.h:63
↓ 140 callersFunctionconcat
include/nlohmann/json.hpp:4277
↓ 131 callersMethodwrite_character
include/nlohmann/json.hpp:14846
↓ 126 callersFunctionto_string
@brief return a string representation of the JSON pointer @sa https://json.nlohmann.me/api/json_pointer/to_string/
include/nlohmann/json.hpp:13749
↓ 122 callersMethoddata
src/storage_view.cc:317
↓ 118 callersMethodsize
include/nlohmann/json.hpp:3109
↓ 99 callersMethodempty
include/ctranslate2/batch_reader.h:143
↓ 93 callersMethodshape
(self)
python/ctranslate2/specs/model_spec.py:632
↓ 71 callersMethodget
src/thread_pool.cc:46
↓ 68 callersMethodrank
include/ctranslate2/storage_view.h:116
↓ 62 callersMethodto_float32
src/storage_view.cc:129
↓ 62 callersMethodtranslate_batch
src/translator.cc:45
↓ 61 callersMethodset_layer_norm
(self, spec, layer_norm)
python/ctranslate2/converters/transformers.py:1352
↓ 59 callersFunctionmax
src/cpu/kernels.cc:298
↓ 54 callersMethodat
src/cpu/primitives.cc:40
↓ 54 callersFunctioncopy
include/ctranslate2/ops/flash-attention/utils.h:299
↓ 53 callersMethodsize
include/ctranslate2/storage_view.h:138
↓ 52 callersFunctionsignal
Signal and silence signaling NaN. \param nan half-precision NaN value \return quiet NaN \exception FE_INVALID if \a nan is signaling NaN
include/half_float/half.hpp:691
↓ 51 callersMethoddtype
(self)
python/ctranslate2/specs/model_spec.py:640
↓ 49 callersFunctionget
include/nlohmann/json.hpp:5271
↓ 44 callersFunctionadd
add a character to token_buffer
include/nlohmann/json.hpp:8702
↓ 44 callersMethodparse_error
include/nlohmann/json.hpp:4439
↓ 44 callersFunctionstring
include/nlohmann/json.hpp:6785
↓ 43 callersFunctionparallel_for
src/cpu/parallel.h:39
↓ 42 callersMethodempty
include/nlohmann/json.hpp:6236
↓ 42 callersFunctiontype_name
@brief return the type as string @sa https://json.nlohmann.me/api/basic_json/type_name/
include/nlohmann/json.hpp:23328
↓ 41 callersMethodnumpy
(self)
python/ctranslate2/specs/model_spec.py:649
↓ 39 callersFunctiondefault_translator
tests/translator_test.cc:102
↓ 38 callersMethodconvert
Converts the model to the CTranslate2 format. Arguments: output_dir: Output directory where the CTranslate2 model is saved.
python/ctranslate2/converters/converter.py:57
↓ 38 callersMethodvalue
return value of the iterator
include/nlohmann/json.hpp:5228
↓ 37 callersFunctionbasic_json
@brief create an empty value with a given type @sa https://json.nlohmann.me/api/basic_json/basic_json/
include/nlohmann/json.hpp:19983
↓ 36 callersMethodset_embeddings
(self, spec, module)
python/ctranslate2/converters/transformers.py:250
↓ 35 callersFunctionmin
src/cpu/kernels.cc:312
↓ 34 callersFunctionis_object
@brief return whether value is an object @sa https://json.nlohmann.me/api/basic_json/is_object/
include/nlohmann/json.hpp:20522
↓ 34 callersFunctionsize
@brief returns the number of elements @sa https://json.nlohmann.me/api/basic_json/size/
include/nlohmann/json.hpp:22114
↓ 33 callersMethodregister_vocabulary
Registers the vocabulary of tokens. Arguments: tokens: List of tokens.
python/ctranslate2/specs/model_spec.py:594
↓ 32 callersMethodfrom_config
Creates the converter from the configuration. Arguments: config: Path to the YAML configuration, or a dictionary with the loaded co
python/ctranslate2/converters/opennmt_tf.py:22
↓ 32 callersMethodget_vocabulary
(self, model, tokenizer)
python/ctranslate2/converters/transformers.py:1257
↓ 30 callersMethodkey
include/nlohmann/json.hpp:7269
↓ 30 callersFunctionmul
src/cpu/kernels.cc:284
↓ 28 callersFunctionget_token_string
return the last read token (for errors only). Will never contain EOF (an arbitrary value that is not a valid char value, often -1), because 255 may l
include/nlohmann/json.hpp:8749
↓ 28 callersFunctioninvalid
Raise domain error and return NaN. return quiet NaN \exception FE_INVALID
include/half_float/half.hpp:743
↓ 27 callersFunction_get_transliterator
()
python/tests/test_translator.py:29
↓ 26 callersFunctionraise
Raise floating-point exception. \param flags exceptions to raise \param cond condition to raise exceptions for
include/half_float/half.hpp:625
↓ 24 callersFunctionend
@brief returns an iterator to one past the last element @sa https://json.nlohmann.me/api/basic_json/end/
include/nlohmann/json.hpp:21961
↓ 24 callersFunctionlog
Natural logarithm. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::log](https://en.cppreference.com/w/
include/half_float/half.hpp:3050
↓ 23 callersMethodget_variable_if_exists
src/models/model.cc:236
↓ 23 callersFunctioninput_adapter
include/nlohmann/json.hpp:6451
↓ 23 callersFunctionisnan
Check for NaN. See also:** Documentation for [std::isnan](https://en.cppreference.com/w/cpp/numeric/math/isnan). \param arg number to check \retval tr
include/half_float/half.hpp:4385
↓ 23 callersMethodtranslate_batch
python/cpp/translator.cc:120
↓ 21 callersMethodget
src/layers/decoder.cc:147
↓ 21 callersFunctionswap
@brief exchanges the values @sa https://json.nlohmann.me/api/basic_json/swap/
include/nlohmann/json.hpp:22632
↓ 20 callersFunctionassert_vector_eq
tests/test_utils.h:56
↓ 20 callersFunctionindex_vector
include/ctranslate2/utils.h:36
↓ 20 callersMethodsax_parse
include/nlohmann/json.hpp:12259
↓ 19 callersMethodadd
src/cpu/vec.h:115
↓ 19 callersMethoddecode
src/decoding.cc:263
↓ 19 callersMethodnumber_integer
include/nlohmann/json.hpp:7239
↓ 19 callersMethodoperator[]
access to successor
include/nlohmann/json.hpp:13651
↓ 18 callersFunctionfrom_json
include/nlohmann/json.hpp:4593
↓ 18 callersMethodnumber_unsigned
include/nlohmann/json.hpp:7244
↓ 18 callersMethodoutput_type
src/layers/common.cc:56
↓ 18 callersMethodto
(self, dtype: str)
python/ctranslate2/specs/model_spec.py:643
↓ 17 callersFunctionabs
Absolute value. See also:** Documentation for [std::abs](https://en.cppreference.com/w/cpp/numeric/math/fabs). \param arg operand \return absolute val
include/half_float/half.hpp:2735
↓ 17 callersMethodget_token_string
! @return a string representation of the last read byte */
include/nlohmann/json.hpp:11975
↓ 17 callersMethodload
src/cpu/vec.h:20
↓ 17 callersFunctionto_json
include/nlohmann/json.hpp:5571
↓ 16 callersFunctionis_array
@brief return whether value is an array @sa https://json.nlohmann.me/api/basic_json/is_array/
include/nlohmann/json.hpp:20529
↓ 15 callersFunctionbegin
@brief returns an iterator to the first element @sa https://json.nlohmann.me/api/basic_json/begin/
include/nlohmann/json.hpp:21936
↓ 15 callersMethodbuffer
src/storage_view.cc:308
↓ 15 callersFunctionclear
@brief clears the contents @sa https://json.nlohmann.me/api/basic_json/clear/
include/nlohmann/json.hpp:22197
↓ 15 callersFunctioncombine
boost::hash_combine
include/nlohmann/json.hpp:5933
↓ 15 callersMethodget_scoped_device_setter
include/ctranslate2/models/model.h:111
↓ 15 callersFunctionis_null
@brief return whether value is null @sa https://json.nlohmann.me/api/basic_json/is_null/
include/nlohmann/json.hpp:20480
↓ 14 callersMethodis_scalar
include/ctranslate2/storage_view.h:144
↓ 14 callersFunctionmayiuse_mkl
src/cpu/backend.cc:28
↓ 14 callersFunctionselect
Select value or signaling NaN. \param x preferred half-precision value \param y ignored half-precision value except for signaling NaN \return \a y if
include/half_float/half.hpp:731
↓ 14 callersFunctionset_parents
include/nlohmann/json.hpp:19871
↓ 13 callersMethodadd_padding
src/padder.cc:66
↓ 13 callersMethodgenerate_batch
python/cpp/generator.cc:14
↓ 13 callersMethodinitial_state
src/layers/transformer.cc:537
↓ 13 callersMethodnum_hypotheses
include/ctranslate2/translation.h:135
↓ 13 callersFunctionreplace
src/models/transformer.cc:8
↓ 12 callersFunctiondevice_cast
src/cuda/helpers.h:64
↓ 12 callersFunctiondtype_name
src/types.cc:14
↓ 12 callersFunctionget_device_index
src/devices.cc:91
↓ 12 callersMethodget_stream
src/batch_reader.cc:28
↓ 12 callersMethodnumber_float
include/nlohmann/json.hpp:7249
↓ 12 callersFunctionpole
Raise pole error and return infinity. \param sign half-precision value with sign bit only \return half-precision infinity with sign of \a sign \except
include/half_float/half.hpp:755
↓ 12 callersMethodset_layer_norm
(self, spec, layer_norm)
python/ctranslate2/converters/transformers.py:3813
next →1–100 of 2,508, ranked by callers