Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/OpenNMT/CTranslate2
/ functions
Functions
2,508 in github.com/OpenNMT/CTranslate2
⨍
Functions
2,508
◇
Types & classes
601
↳
Endpoints
4
Method
architecture_name
(self)
python/ctranslate2/converters/transformers.py:2912
Method
architecture_name
(self)
python/ctranslate2/converters/transformers.py:3084
Method
architecture_name
(self)
python/ctranslate2/converters/transformers.py:3233
Method
architecture_name
(self)
python/ctranslate2/converters/transformers.py:3291
Method
architecture_name
(self)
python/ctranslate2/converters/transformers.py:3370
Method
architecture_name
(self)
python/ctranslate2/converters/transformers.py:3452
Method
architecture_name
(self)
python/ctranslate2/converters/transformers.py:3534
Method
architecture_name
(self)
python/ctranslate2/converters/transformers.py:3810
Method
architecture_name
(self)
python/ctranslate2/converters/transformers.py:4072
Function
area
include/half_float/half.hpp:1788
Function
array_equal
(a, b)
python/tests/test_utils.py:31
Method
as_scalar
include/ctranslate2/storage_view.h:215
Method
as_sequence_encoder
src/models/transformer.cc:134
Method
as_sequence_generator
src/models/transformer.cc:111
Method
as_sequence_to_sequence
src/models/transformer.cc:82
Function
asin
Arc sine. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::asin](https://en.cppreference.com/w/cpp/nume
include/half_float/half.hpp:3654
Function
asinh
Hyperbolic area sine. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::asinh](https://en.cppreference.c
include/half_float/half.hpp:3880
Method
assert_model_is_ready
python/cpp/replica_pool.h:190
Function
atan
Arc tangent function. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::atan](https://en.cppreference.co
include/half_float/half.hpp:3708
Function
atanh
Hyperbolic area tangent. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::atanh](https://en.cppreferenc
include/half_float/half.hpp:3933
Function
avg_tokens
(generated_token)
tools/benchmark_tensor_parallel/benchmark.py:44
Function
back
@brief access the last element @sa https://json.nlohmann.me/api/basic_json/back/
include/nlohmann/json.hpp:21574
Function
basic_json array
@brief explicitly create an array from an initializer list @sa https://json.nlohmann.me/api/basic_json/array/
include/nlohmann/json.hpp:20169
Function
basic_json binary
@brief explicitly create a binary array (without subtype) @sa https://json.nlohmann.me/api/basic_json/binary/
include/nlohmann/json.hpp:20125
Function
basic_json diff
@brief creates a diff as a JSON patch @sa https://json.nlohmann.me/api/basic_json/diff/
include/nlohmann/json.hpp:24126
Function
basic_json from_bjdata
include/nlohmann/json.hpp:23674
Function
basic_json from_bson
include/nlohmann/json.hpp:23704
Function
basic_json from_cbor
include/nlohmann/json.hpp:23506
Function
basic_json from_msgpack
include/nlohmann/json.hpp:23565
Function
basic_json from_ubjson
include/nlohmann/json.hpp:23619
Function
basic_json meta
@brief returns version information on the library @sa https://json.nlohmann.me/api/basic_json/meta/
include/nlohmann/json.hpp:19423
Function
basic_json object
@brief explicitly create an object from an initializer list @sa https://json.nlohmann.me/api/basic_json/object/
include/nlohmann/json.hpp:20177
Function
basic_json parse
include/nlohmann/json.hpp:23185
Method
batch_size
src/layers/decoder.cc:64
Function
beam_to_test_name
tests/translator_test.cc:18
Method
bfloat16_t
include/ctranslate2/bfloat16.h:21
Method
bfloat16_t>
include/ctranslate2/ops/flash-attention/utils.h:54
Function
binary
include/nlohmann/json.hpp:6791
Method
binary
include/nlohmann/json.hpp:6975
Method
binary_reader
! @brief create a binary reader @param[in] adapter input adapter to read from */
include/nlohmann/json.hpp:9158
Function
binary_transform
src/cpu/parallel.h:109
Function
binary_transform
src/cuda/helpers.h:79
Method
binary_writer
! @brief create a binary writer @param[in] adapter output adapter to write to */
include/nlohmann/json.hpp:14966
Method
bind_right
src/cuda/helpers.h:161
Method
bit_and
src/cpu/vec.h:55
Method
bit_and
src/cpu/vec_avx512.h:58
Method
bit_and
src/cpu/vec_neon.h:74
Method
bit_and
src/cpu/vec_avx.h:99
Function
bit_cast
include/ctranslate2/bfloat16.h:13
Method
bit_xor
src/cpu/vec.h:59
Method
bit_xor
src/cpu/vec_avx512.h:62
Method
bit_xor
src/cpu/vec_neon.h:78
Method
bit_xor
src/cpu/vec_avx.h:103
Function
block_reduce
src/cuda/helpers.h:413
Function
boolean
include/nlohmann/json.hpp:6761
Method
boolean
include/nlohmann/json.hpp:6945
Method
buffer_loop
src/buffered_translation_wrapper.cc:68
Function
build_layers_list
include/ctranslate2/layers/common.h:26
Function
build_optional_layer
include/ctranslate2/layers/common.h:17
Method
calc_bson_array_size
! @return The size of the BSON-encoded array @a value */
include/nlohmann/json.hpp:16022
Method
calc_bson_binary_size
! @return The size of the BSON-encoded binary array @a value */
include/nlohmann/json.hpp:16037
Method
calc_bson_element_size
! @brief Calculates the size necessary to serialize the JSON value @a j with its @a name @return The calculated size for the BSON document ent
include/nlohmann/json.hpp:16079
Method
calc_bson_entry_header_size
! @return The size of a BSON document entry header, including the id marker and the entry name size (and its null-terminator). */
include/nlohmann/json.hpp:15875
Method
calc_bson_integer_size
! @return The size of the BSON-encoded integer @a value */
include/nlohmann/json.hpp:15952
Method
calc_bson_object_size
! @brief Calculates the size of the BSON serialization of the given JSON-object @a j. @param[in] value JSON value to serialize
include/nlohmann/json.hpp:16174
Method
calc_bson_string_size
! @return The size of the BSON-encoded string in @a value */
include/nlohmann/json.hpp:15922
Method
calc_bson_unsigned_size
! @return The size of the BSON-encoded unsigned integer in @a j */
include/nlohmann/json.hpp:15980
Method
can_get_job
src/thread_pool.cc:33
Method
cast
include/half_float/half.hpp:2298
Method
cast
include/half_float/half.hpp:2310
Method
cast
include/half_float/half.hpp:2318
Method
cast_impl
include/half_float/half.hpp:2301
Method
cast_impl
include/half_float/half.hpp:2313
Function
cbrt
Cubic root. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::cbrt](https://en.cppreference.com/w/cpp/nu
include/half_float/half.hpp:3264
Function
ceil
Nearest integer not less than half value. See also:** Documentation for [std::ceil](https://en.cppreference.com/w/cpp/numeric/math/ceil). \param arg h
include/half_float/half.hpp:4071
Method
check_arguments
src/ops/split.cc:80
Method
check_arguments
src/ops/slide.cc:41
Method
clear_cache
src/cuda/allocator.cc:71
Method
clear_cache
Clears the cache of each worker. This method is not thread-safe.
include/ctranslate2/replica_pool.h:141
Function
clear_subtype
@brief clears the binary subtype @sa https://json.nlohmann.me/api/byte_container_with_subtype/clear_subtype/
include/nlohmann/json.hpp:5889
Function
clear_transformers_cache
Clears the Transformers model cache after each test when running in a CI.
python/tests/test_transformers.py:14
Method
clone
src/models/wav2vec2.cc:45
Method
clone
src/models/whisper.cc:44
Method
clone
src/models/wav2vec2bert.cc:45
Method
clone
src/models/transformer.cc:92
Method
clone
tests/attention_test.cc:30
Method
clone
tests/attention_test.cc:151
Method
clone_models
python/cpp/replica_pool.h:173
Function
combine_attn_seqk_parallel
include/ctranslate2/ops/flash-attention/flash_fwd_kernel.h:1048
Method
combine_heads
src/layers/flash_attention.cc:157
Method
combine_heads
src/layers/attention.cc:823
Method
compensate_u8_input
src/ops/gemm.cc:170
Method
compute
src/ops/rms_norm_cpu.cc:9
Method
compute
src/ops/alibi_add_cpu.cc:9
Method
compute
src/ops/topk_cpu.cc:13
Method
compute
src/ops/multinomial_cpu.cc:27
Method
compute
src/ops/softmax_cpu.cc:9
Method
compute
src/ops/gather_cpu.cc:10
Method
compute
src/ops/median_filter_cpu.cc:13
Method
compute
src/ops/bias_add_cpu.cc:7
← previous
next →
1,201–1,300 of 2,508, ranked by callers