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
Function
dequantize_gemm_output_row
src/cpu/kernels.cc:654
Method
device
Device management.
include/ctranslate2/storage_view.h:83
Method
device
include/ctranslate2/layers/decoder.h:75
Method
device_index
include/ctranslate2/storage_view.h:87
Method
diagnostics
include/nlohmann/json.hpp:4321
Method
dispatch
src/ops/multinomial.cc:22
Method
div
src/cpu/vec.h:127
Method
div
src/cpu/vec_avx512.h:130
Method
div
src/cpu/vec_neon.h:146
Method
div
src/cpu/vec_avx.h:172
Method
diyfp
include/nlohmann/json.hpp:16847
Method
dtype
(self)
python/ctranslate2/specs/model_spec.py:683
Method
dtype
(self)
python/ctranslate2/specs/model_spec.py:737
Method
empty
include/ctranslate2/batch_reader.h:40
Method
encode
python/cpp/wav2vec2.cc:14
Method
encode
python/cpp/wav2vec2bert.cc:14
Method
encode
src/models/wav2vec2.cc:68
Method
encode
src/models/sequence_to_sequence.cc:216
Method
encode
src/models/wav2vec2bert.cc:68
Function
end_array
include/nlohmann/json.hpp:6841
Method
end_array
include/nlohmann/json.hpp:7069
Function
end_object
include/nlohmann/json.hpp:6819
Method
end_object
include/nlohmann/json.hpp:7016
Method
ensure_dtype
src/models/model.cc:304
Method
erf
src/cpu/vec.h:103
Method
erf
src/cpu/vec_avx512.h:106
Method
erf
src/cpu/vec_neon.h:122
Method
erf
src/cpu/vec_avx.h:148
Function
erfc
Complementary error function. This function may be 1 ULP off the correctly rounded exact result for any rounding mode in <0.5% of inputs. See also:**
include/half_float/half.hpp:3988
Method
exception_message
! @param[in] format the current format @param[in] detail a detailed error message @param[in] context further context information
include/nlohmann/json.hpp:11988
Method
exception_message
include/nlohmann/json.hpp:12564
Method
exp
src/cpu/vec.h:83
Method
exp
src/cpu/vec_avx512.h:86
Method
exp
src/cpu/primitives.cc:358
Method
exp
src/cpu/vec_neon.h:102
Method
exp
src/cpu/vec_avx.h:128
Function
exp2_post
include/half_float/half.hpp:1688
Function
exp<TARGET_ISA>
src/cpu/kernels.cc:215
Function
expm1
Exponential minus one. This function may be 1 ULP off the correctly rounded exact result in <0.05% of inputs for `std::round_to_nearest` and in <1% of
include/half_float/half.hpp:2997
Method
f31
include/half_float/half.hpp:1847
Function
fdim
Positive difference. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::fdim](https://en.cppreference.com
include/half_float/half.hpp:2904
Function
feclearexcept
Clear exception flags. This function works even if [automatic exception flag handling](\ref HALF_ERRHANDLING_FLAGS) is disabled, but in that case manu
include/half_float/half.hpp:4518
Function
fegetexceptflag
Save exception flags. This function works even if [automatic exception flag handling](\ref HALF_ERRHANDLING_FLAGS) is disabled, but in that case manua
include/half_float/half.hpp:4548
Function
fesetexceptflag
Restore exception flags. This only copies the specified exception state (including unset flags) without incurring any additional exception handling. T
include/half_float/half.hpp:4559
Function
fetestexcept
Test exception flags. This function works even if [automatic exception flag handling](\ref HALF_ERRHANDLING_FLAGS) is disabled, but in that case manua
include/half_float/half.hpp:4527
Function
fethrowexcept
Throw C++ exceptions based on set exception flags. This function manually throws a corresponding C++ exception if one of the specified flags is set, n
include/half_float/half.hpp:4572
Method
fill_batch_with_fixed_increment
src/batch_reader.cc:38
Method
fill_batch_with_variable_increment
src/batch_reader.cc:60
Method
fill_buffer
UTF-32
include/nlohmann/json.hpp:6250
Method
fill_buffer
UTF-16
include/nlohmann/json.hpp:6308
Method
fill_buffer
include/nlohmann/json.hpp:6397
Method
finalize
src/devices.cc:206
Method
finalize
Called after the work loop.
include/ctranslate2/thread_pool.h:69
Method
finalize
include/ctranslate2/replica_pool.h:355
Function
fix_pybind11_signatures
( app, what, name, obj, options, signature, return_annotation )
docs/conf.py:44
Function
fixed2half
include/half_float/half.hpp:884
Function
flash_fwd_kernel
include/ctranslate2/ops/flash-attention/flash_fwd_launch_template.h:15
Function
flash_fwd_splitkv_combine_kernel
include/ctranslate2/ops/flash-attention/flash_fwd_launch_template.h:37
Function
flash_fwd_splitkv_kernel
include/ctranslate2/ops/flash-attention/flash_fwd_launch_template.h:27
Function
float2half
include/half_float/half.hpp:1064
Function
float2half_impl
include/half_float/half.hpp:907
Function
fma
Fused multiply add. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::fma](https://en.cppreference.com/w
include/half_float/half.hpp:2809
Function
fmax
Maximum of half expressions. See also:** Documentation for [std::fmax](https://en.cppreference.com/w/cpp/numeric/math/fmax). \param x first operand \p
include/half_float/half.hpp:2878
Function
fmin
Minimum of half expressions. See also:** Documentation for [std::fmin](https://en.cppreference.com/w/cpp/numeric/math/fmin). \param x first operand \p
include/half_float/half.hpp:2890
Function
fmod
Remainder of division. See also:** Documentation for [std::fmod](https://en.cppreference.com/w/cpp/numeric/math/fmod). \param x first operand \param y
include/half_float/half.hpp:2743
Method
forward_batch
python/cpp/generator.cc:98
Method
forward_batch_async
src/generator.cc:43
Method
forward_impl
src/models/language_model.cc:352
Function
fp_test_name
tests/test_utils.h:79
Method
free
src/cpu/allocator.cc:36
Method
free
src/cuda/allocator.cc:67
Method
free
src/cuda/allocator.cc:104
Method
free
include/ctranslate2/allocator.h:19
Function
from_bson
include/nlohmann/json.hpp:23734
Function
from_cbor
include/nlohmann/json.hpp:23538
Method
from_config
Creates a Transformer decoder model specification. Args: num_layers: Number of decoder layers. num_heads: Number of atten
python/ctranslate2/specs/transformer_spec.py:629
Method
from_json
include/nlohmann/json.hpp:5766
Method
from_json_file
src/vocabulary.cc:32
Function
from_json_tuple_impl_base
include/nlohmann/json.hpp:4933
Function
from_msgpack
include/nlohmann/json.hpp:23595
Method
from_text_file
src/vocabulary.cc:9
Function
from_ubjson
include/nlohmann/json.hpp:23649
Function
front
@brief access the first element @sa https://json.nlohmann.me/api/basic_json/front/
include/nlohmann/json.hpp:21560
Function
fuse_linear
(spec, layers)
python/ctranslate2/converters/utils.py:4
Function
fuse_linear_prequant
(spec, layers, axis)
python/ctranslate2/converters/utils.py:38
Function
gamma
include/half_float/half.hpp:1937
Function
gather_batch_inplace
src/ops/gather.cc:30
Method
gelu
src/cpu/primitives.cc:305
Function
gelu<TARGET_ISA>
src/cpu/kernels.cc:240
Method
gelu_sigmoid
src/cpu/primitives.cc:323
Function
gelu_sigmoid<TARGET_ISA>
src/cpu/kernels.cc:250
Method
gelu_tanh
src/cpu/primitives.cc:314
Function
gelu_tanh<TARGET_ISA>
src/cpu/kernels.cc:245
Method
gemm
src/cpu/primitives.cc:646
Method
gemm_batch_strided
src/cpu/primitives.cc:1077
Method
gemm_pack_b
src/cpu/primitives.cc:554
Method
generate
src/models/language_model.cc:55
Function
generator_async_generate_tokens
Yields tokens asynchronously as they are generated by the model. Arguments: prompt: Batch of start tokens. If the decoder starts from a
python/ctranslate2/extensions.py:351
Function
generator_generate_iterable
Generates from an iterable of tokenized prompts. This method is built on top of :meth:`ctranslate2.Generator.generate_batch` to efficiently r
python/ctranslate2/extensions.py:130
Function
generator_generate_tokens
Yields tokens as they are generated by the model. Arguments: prompt: Batch of start tokens. If the decoder starts from a special st
python/ctranslate2/extensions.py:270
← previous
next →
1,401–1,500 of 2,508, ranked by callers