Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/NVIDIA/cutlass
/ functions
Functions
19,553 in github.com/NVIDIA/cutlass
⨍
Functions
19,553
◇
Types & classes
10,397
↳
Endpoints
26
↓ 1,758 callers
Function
print
examples/77_blackwell_fmha/common/pow_2.hpp:81
↓ 1,617 callers
Function
make_tensor
include/cute/tensor_impl.hpp:396
↓ 1,287 callers
Method
host_view
Accesses the tensor reference pointing to data
tools/util/include/cutlass/util/host_tensor.h:314
↓ 1,015 callers
Method
append
Inserts the operation. operation_kind -> configuration_name -> []
python/cutlass_library/manifest.py:701
↓ 990 callers
Method
size
examples/77_blackwell_fmha/reference/reference_abs_error.hpp:76
↓ 964 callers
Method
k
(self)
python/cutlass_cppgen/shape.py:95
↓ 776 callers
Method
at
Accesses an element by coordinate
include/cutlass/matrix.h:148
↓ 747 callers
Function
size
include/cute/layout.hpp:605
↓ 724 callers
Function
make_layout
include/cute/layout.hpp:333
↓ 722 callers
Function
copy
include/cute/algorithm/copy.hpp:171
↓ 716 callers
Method
n
(self)
python/cutlass_cppgen/shape.py:91
↓ 696 callers
Method
make_layout
examples/common/gather_tensor.hpp:130
↓ 632 callers
Method
get_slice
include/cute/atom/mma_atom.hpp:357
↓ 625 callers
Method
m
(self)
python/cutlass_cppgen/shape.py:87
↓ 596 callers
Function
rank
include/cute/layout.hpp:614
↓ 591 callers
Function
make_smem_ptr
include/cute/pointer.hpp:165
↓ 573 callers
Function
shape
include/cute/int_tuple.hpp:102
↓ 528 callers
Method
partition_S
include/cute/atom/copy_atom.hpp:366
↓ 525 callers
Method
data
include/cute/tensor_impl.hpp:180
↓ 520 callers
Method
data
include/cutlass/gemm/kernel/sm90_tile_scheduler.hpp:64
↓ 517 callers
Method
copy
examples/88_hopper_fmha/kernel/fmha_kernel_bwd_convert.hpp:103
↓ 509 callers
Method
column
include/cutlass/matrix.h:2094
↓ 508 callers
Function
make_layout
(*layouts)
python/pycute/layout.py:116
↓ 500 callers
Method
partition_D
include/cute/atom/copy_atom.hpp:376
↓ 475 callers
Method
row
include/cutlass/matrix.h:229
↓ 441 callers
Method
at
Gets the value pointed to
tools/profiler/src/problem_space.cpp:129
↓ 439 callers
Method
data
tools/library/include/cutlass/library/util.h:266
↓ 439 callers
Function
printf
Print one or more values with optional formatting. This function provides printf-style formatted printing capabilities. It can print values
python/CuTeDSL/cutlass/cute/core.py:2040
↓ 402 callers
Method
sync_device
Copies data from host to device
tools/util/include/cutlass/util/host_tensor.h:403
↓ 398 callers
Method
to
Convert the ratio to another type. :param dtype: The target type for conversion :type dtype: type :return: The ratio converte
python/CuTeDSL/cutlass/cute/core.py:688
↓ 389 callers
Method
advance
Move to the next pipeline stage.
python/CuTeDSL/cutlass/pipeline/sm90.py:1017
↓ 347 callers
Method
consumer_wait
examples/112_blackwell_ssd/utils/pipeline.h:167
↓ 344 callers
Method
consumer_release
( self, state: PipelineState, *, loc: Optional[ir.Location] = None, ip
python/CuTeDSL/cutlass/pipeline/sm90.py:282
↓ 339 callers
Function
local_tile
include/cute/tensor_impl.hpp:1035
↓ 333 callers
Method
stride
Returns the stride of the layout
include/cutlass/layout/matrix.h:119
↓ 328 callers
Method
begin
Before entry of the subtile load loop
include/cutlass/epilogue/fusion/sm90_visitor_tma_warpspecialized.hpp:132
↓ 320 callers
Method
index
include/cutlass/pipeline/sm90_pipeline.hpp:188
↓ 320 callers
Function
synclog_emit_wgmma_reg_smem
include/cutlass/arch/synclog.hpp:898
↓ 320 callers
Function
synclog_emit_wgmma_smem_smem
include/cutlass/arch/synclog.hpp:916
↓ 311 callers
Function
size
(layout)
python/pycute/layout.py:125
↓ 306 callers
Method
producer_acquire
examples/112_blackwell_ssd/utils/pipeline.h:136
↓ 297 callers
Function
elect_one_sync
Elect one thread in the warp. The elected thread gets its predicate set to true, all others obtain false.
include/cute/arch/cluster_sm90.hpp:180
↓ 292 callers
Method
with
include/cute/atom/mma_atom.hpp:76
↓ 282 callers
Function
enum_auto
()
python/cutlass_library/library.py:49
↓ 276 callers
Method
device_data
Gets pointer to device data
tools/util/include/cutlass/util/host_tensor.h:286
↓ 269 callers
Method
device_ref
Accesses the tensor reference pointing to data
tools/util/include/cutlass/util/host_tensor.h:304
↓ 269 callers
Method
resize
Changes the size of the logical tensor. Only allocates memory if new capacity exceeds reserved capacity. To force allocation, call reset().
tools/util/include/cutlass/util/host_tensor.h:228
↓ 264 callers
Function
min
include/cute/int_tuple.hpp:154
↓ 263 callers
Method
make_pipeline_state
include/cutlass/pipeline/sm90_pipeline.hpp:247
↓ 263 callers
Function
max
include/cute/int_tuple.hpp:134
↓ 248 callers
Method
imag
Set the imaginary part of the complex number
include/cutlass/complex.h:315
↓ 247 callers
Function
to_underlying_arguments
include/cutlass/gemm/kernel/sm100_tile_scheduler_stream_k.hpp:114
↓ 245 callers
Method
data_ptr
Get the data pointer from the tensor value. Extracts the data pointer (first field) from the LLVM struct value. :param loc: Optional
examples/python/CuTeDSL/dsl_tutorials/ffi/jit_argument.py:77
↓ 243 callers
Method
size_in_bytes
Returns the size of the union in bytes. :return: The size of the union.
python/CuTeDSL/cutlass/cute/core.py:6134
↓ 241 callers
Function
at
()
docs/jquery.js:23
↓ 239 callers
Function
print
include/cute/layout.hpp:1918
↓ 237 callers
Function
Element
Unpacks an element from memory
include/cutlass/subbyte_reference.h:187
↓ 235 callers
Function
from_dlpack
Convert from tensor object supporting __dlpack__() to a CuTe Tensor. :param tensor_dlpack: Tensor object that supports the DLPack protocol :t
python/CuTeDSL/cutlass/cute/runtime.py:749
↓ 234 callers
Method
real
Set the real part of the complex number
include/cutlass/complex.h:311
↓ 230 callers
Method
index
(self)
python/CuTeDSL/cutlass/pipeline/helpers.py:697
↓ 230 callers
Method
producer_commit
NOP for TMA based mainloop
examples/112_blackwell_ssd/utils/pipeline.h:142
↓ 223 callers
Method
get
Returns a pointer to the managed object
tools/util/include/cutlass/util/device_memory.h:251
↓ 220 callers
Method
at
Returns a reference to the element at the logical Coord in host memory
tools/util/include/cutlass/util/host_tensor.h:375
↓ 216 callers
Function
make_gmem_ptr
include/cute/pointer.hpp:102
↓ 215 callers
Function
append
include/cute/layout_composed.hpp:308
↓ 214 callers
Function
print
include/cute/atom/mma_atom.hpp:656
↓ 211 callers
Method
get_tma_tensor
include/cute/atom/copy_traits_sm90_tma.hpp:150
↓ 209 callers
Method
create
Create a MoE persistent tile scheduler. :param params: Scheduler parameters (from host) :param offs: Cumsum tensor o
examples/python/CuTeDSL/cute/blackwell/kernel/moe/moe_persistent_scheduler.py:417
↓ 208 callers
Method
mn
Obtains a Coord<2> from GemmCoord
include/cutlass/gemm_coord.h:162
↓ 206 callers
Method
n
tools/profiler/include/cutlass/profiler/grouped_gemm_operation_profiler.h:111
↓ 204 callers
Method
get_tma_descriptor
Return TmaDescriptor/TensorMap
include/cute/atom/copy_traits_sm90_tma.hpp:198
↓ 200 callers
Function
print
include/cutlass/conv/convnd_problem_shape.hpp:579
↓ 200 callers
Method
set
Sets runtime fields of the Atom. Some Atoms have runtime state, for example a tcgen05 MMA Atom .. code-block:: python
python/CuTeDSL/cutlass/cute/atom.py:200
↓ 198 callers
Function
can_implement
include/cutlass/gemm/kernel/sm100_tile_scheduler_stream_k.hpp:220
↓ 195 callers
Method
ir_value
( self, *, loc: Optional[ir.Location] = None, ip: Optional[ir.InsertionPoint]
python/CuTeDSL/cutlass/cute/experimental/core.py:24
↓ 194 callers
Function
filter_zeros
include/cute/layout.hpp:915
↓ 193 callers
Method
numel
Total number of elements (product of all shape dimensions).
python/CuTeDSL/cutlass/base_dsl/_mlir_helpers/arith.py:1184
↓ 188 callers
Function
gemm
include/cute/algorithm/gemm.hpp:68
↓ 186 callers
Method
stride
Returns the layout object's stride vector
tools/util/include/cutlass/util/host_tensor.h:350
↓ 179 callers
Method
reset
Clears the HostTensor allocation to size/capacity = 0
tools/util/include/cutlass/util/host_tensor.h:168
↓ 177 callers
Method
m
tools/profiler/include/cutlass/profiler/grouped_gemm_operation_profiler.h:110
↓ 172 callers
Method
from_tensor
(tensor: cute.Tensor)
python/CuTeDSL/cutlass/utils/layout.py:51
↓ 171 callers
Function
transform
include/cute/algorithm/tuple_algorithms.hpp:205
↓ 170 callers
Method
add_tile_offset
include/cutlass/epilogue/threadblock/shared_load_iterator_mixed.h:185
↓ 168 callers
Function
TensorNorm
tools/util/include/cutlass/util/reference/host/tensor_reduce.h:154
↓ 168 callers
Method
host_ref
Accesses the tensor reference pointing to data
tools/util/include/cutlass/util/host_tensor.h:298
↓ 168 callers
Function
round_nearest
include/cutlass/fast_math.h:151
↓ 165 callers
Method
shape
include/cute/tensor_impl.hpp:198
↓ 164 callers
Function
get_workspace_size
include/cutlass/gemm/kernel/sm90_tile_scheduler.hpp:139
↓ 159 callers
Method
data
include/cutlass/epilogue/collective/detail.hpp:171
↓ 158 callers
Function
convert
(src: Tensor, dst: Tensor)
python/CuTeDSL/cutlass/cute/testing.py:617
↓ 157 callers
Method
partition_A
include/cute/atom/mma_atom.hpp:476
↓ 154 callers
Method
k
tools/profiler/include/cutlass/profiler/grouped_gemm_operation_profiler.h:112
↓ 153 callers
Method
empty
include/cute/container/array.hpp:153
↓ 153 callers
Method
partition_B
include/cute/atom/mma_atom.hpp:487
↓ 150 callers
Method
w
Accesses the real part of the quaternion
include/cutlass/quaternion.h:188
↓ 149 callers
Function
cast_smem_ptr_to_uint
CUTE helper to cast SMEM pointer to unsigned
include/cute/arch/util.hpp:91
↓ 149 callers
Method
get
examples/77_blackwell_fmha/reference/reference_abs_error.hpp:61
↓ 148 callers
Function
add_tile_offset
include/cutlass/epilogue/threadblock/shared_load_iterator.h:155
↓ 148 callers
Function
product
(a)
python/pycute/int_tuple.py:65
next →
1–100 of 19,553, ranked by callers