Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/alibaba/BladeDISC
/ functions
Functions
6,088 in github.com/alibaba/BladeDISC
⨍
Functions
6,088
◇
Types & classes
1,279
↳
Endpoints
6
↓ 3 callers
Function
_get_minimal_slice_set
Produces an ordered sequence of tensor slices that, when used in sequence on a tensor with shape dims, yields tensors that contain e
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/model/modules/utils.py:127
↓ 3 callers
Method
_get_norm
r""" Compute the norm of the values uniformaly distributed between delta_begin and delta_end. Currently only L2 norm is suppor
tools/torch_quant/torch_quant/observer.py:437
↓ 3 callers
Function
_is_tensor_or_const
(val, support_number_inpts_outs)
pytorch_blade/torch_blade/clustering/support_fusion_algorithm.py:102
↓ 3 callers
Method
_locate_lib_tao_ops
Try to find libtao_ops.so under tao build path.
tao/tao_bridge/test/tao_ut_common.py:51
↓ 3 callers
Method
_maxpool2d
(self, x: tf.Tensor, k: int = 2)
tensorflow_blade/tests/tf_test_common.py:30
↓ 3 callers
Function
_set_opset_version_from_config
Consulting cfg.customize_onnx_opset_version and set global ONNX opset version. And return the opset version.
pytorch_blade/torch_blade/pass_manager.py:61
↓ 3 callers
Method
_test_dynamic_shape_engines
(self, model, shapes)
pytorch_blade/tests/tensorrt/test_holder_serialize.py:64
↓ 3 callers
Method
_test_func_has_alpha
(self, torch_func)
pytorch_blade/tests/disc/ops/test_binary_ops.py:127
↓ 3 callers
Method
_test_layer_norm
(self, layernorm)
pytorch_blade/tests/disc/ops/test_layer_norm.py:19
↓ 3 callers
Method
_test_list_config
(self, attr, vals)
pytorch_blade/tests/test_config.py:46
↓ 3 callers
Method
_test_mem_ops
(self, reshape_func, dtype=None, x=None)
pytorch_blade/tests/disc/ops/test_mem_ops.py:21
↓ 3 callers
Method
_test_rank0_broadcast
(self, broadcast_func)
pytorch_blade/tests/disc/ops/test_broadcast.py:20
↓ 3 callers
Function
_write
(line, cmd="build")
scripts/python/tao_build.py:187
↓ 3 callers
Function
add_binary_op
( graph_def: tf.GraphDef, op_type: OpType, input_name_list: List[str], name: str, data_typ
tensorflow_blade/tf_blade/util/tf_graph_transform_util.py:179
↓ 3 callers
Function
add_const
( graph_def: tf.GraphDef, array: np.ndarray, name: str, data_type: tf.DType )
tensorflow_blade/tf_blade/util/tf_graph_transform_util.py:235
↓ 3 callers
Function
append_env_var
(name, new_part)
scripts/python/tao_common.py:123
↓ 3 callers
Method
apply_unifold_original_mode
(self)
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/model/modules/outer_product_mean.py:71
↓ 3 callers
Function
atomicMax
tao_compiler/mlir/xla/ral/context/custom_library/atomic.cu.h:15
↓ 3 callers
Function
backwardPermutation
tao_compiler/mlir/disc/transforms/disc_transpose_simplifier.cc:377
↓ 3 callers
Function
backwardTransposePermutation
tao_compiler/mlir/disc/transforms/disc_transpose_simplifier.cc:359
↓ 3 callers
Function
bazel_build
(target, flag="")
scripts/python/tao_build.py:292
↓ 3 callers
Function
benchmark
(model, inp)
examples/PyTorch/Quantization/bert_ptq.py:47
↓ 3 callers
Method
bindOutput
tao_compiler/mlir/xla/ral/context/base/base_context.cc:73
↓ 3 callers
Method
buffer
Inherited methods overridden :
tao_compiler/mlir/xla/ral/context/common_context_impl_acl.cc:80
↓ 3 callers
Method
build
BUILD-MAX-HEAPIFY in Cormen
tao_compiler/mlir/xla/ral/context/custom_library/tf_topk.cu.h:158
↓ 3 callers
Function
buildDecomposeVectors
tao_compiler/mlir/disc/transforms/disc_transform_schedule.cc:257
↓ 3 callers
Function
build_mkldnn
(root)
scripts/python/common_setup.py:341
↓ 3 callers
Function
ceilDiv
tao_compiler/mlir/disc/tools/disc-transform/LinalgExt/LinalgExtOps.cc:106
↓ 3 callers
Function
ci_build_flag
()
scripts/python/common_setup.py:207
↓ 3 callers
Method
cluster_size
The number of TF nodes in this cluster.
tao/tao_bridge/passes/tao_mark_for_compilation_pass.cc:180
↓ 3 callers
Function
convertConditionalGenericOpToGenericOp
tao_compiler/mlir/disc/tools/disc-transform/TransformOps/TransformOpsExt.cc:2870
↓ 3 callers
Function
convertMemRefToTensorType
tao_compiler/mlir/disc/tools/disc-transform/transforms/legalize_lmhlo_fusion_to_linalg.cc:65
↓ 3 callers
Function
convert_dummy_inputs
convert inputs to torch.Tensor
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/optimization/utils.py:69
↓ 3 callers
Function
convert_load_model
(model)
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/optimization/distributed/convert.py:164
↓ 3 callers
Function
createDiscConvertShapeToStandardPass
tao_compiler/mlir/disc/transforms/disc_shape_to_std.cc:457
↓ 3 callers
Function
createViewLike
tao_compiler/mlir/disc/disc_util.cc:426
↓ 3 callers
Function
create_key
tao_compiler/mlir/xla/ral/context/mkldnn/ideep/ideep/utils.hpp:227
↓ 3 callers
Method
ctx
tao/tao_bridge/executable.h:169
↓ 3 callers
Function
decomposeSplits
pytorch_blade/pytorch_blade/torch-mlir/lib/Dialect/TorchConversion/Transforms/DiscDecomposeComplexOps.cpp:103
↓ 3 callers
Method
defunctionalize
tao/tao_bridge/passes/defunctionalize_control_flow.cc:22
↓ 3 callers
Method
effective_cluster_size
The size of the cluster excluding constant and identity nodes.
tao/tao_bridge/passes/tao_mark_for_compilation_pass.cc:186
↓ 3 callers
Function
emitAttr
tao_compiler/mlir/disc/transforms/disc_lower_to_library_call.cc:825
↓ 3 callers
Method
emitDeviceConstant
tao_compiler/mlir/xla/ral/ral_metadata.cc:149
↓ 3 callers
Method
emitHostConstant
tao_compiler/mlir/xla/ral/ral_metadata.cc:133
↓ 3 callers
Function
ensure_empty_dir
Make sure the given directory exists and is empty. This function will create an empty directory if the directory doesn't exits, or it wil
scripts/python/common_setup.py:153
↓ 3 callers
Function
ensure_empty_dir
Make sure the given directory exists and is empty. This function will create an empty directory if the directory doesn't exits, or it wil
pytorch_blade/common_setup.py:153
↓ 3 callers
Function
evaluate
(model, dataloader, device)
examples/PyTorch/Quantization/bert_ptq.py:62
↓ 3 callers
Method
forward
(self, x)
pytorch_blade/tests/ltc/test_mnist.py:43
↓ 3 callers
Method
fuse
(self, grp_i: int, grp_j: int)
pytorch_blade/torch_blade/clustering/support_fusion_algorithm.py:58
↓ 3 callers
Method
generateResultTileValue
tao_compiler/mlir/disc/tools/disc-transform/LinalgExt/LinalgExtOps.cc:790
↓ 3 callers
Method
getDeviceConstant
tao_compiler/mlir/xla/ral/ral_metadata.cc:108
↓ 3 callers
Method
getDriver
tao_compiler/mlir/xla/ral/ral_context.cc:199
↓ 3 callers
Function
getFusionTagStr
tao_compiler/mlir/disc/transforms/fusion_utils.cc:277
↓ 3 callers
Method
getPatternKind
tao_compiler/mlir/disc/transforms/disc_transform_schedule.cc:1404
↓ 3 callers
Method
getRefinedType
tao_compiler/mlir/disc/transforms/shape_utils.cc:53
↓ 3 callers
Method
getRefinedType
tao_compiler/mlir/disc/transforms/disc_shape_optimization.cc:1419
↓ 3 callers
Function
getReversePermutation
tao_compiler/mlir/disc/transforms/disc_transpose_simplifier.cc:214
↓ 3 callers
Function
getRootMemRef
tao_compiler/mlir/disc/disc_util.cc:70
↓ 3 callers
Function
getRowReductionScheduleHint
tao_compiler/mlir/disc/transforms/codegen_utils.cc:33
↓ 3 callers
Function
getSliceProducer
tao_compiler/mlir/disc/tools/disc-transform/TransformOps/TransformOpsExt.cc:278
↓ 3 callers
Method
getSymbolDim
tao_compiler/mlir/disc/transforms/shape_utils.h:62
↓ 3 callers
Function
getTransposeOutputType
tao_compiler/mlir/disc/transforms/disc_transpose_simplifier.cc:239
↓ 3 callers
Function
get_const_value
(node: tf.NodeDef)
tensorflow_blade/tf_blade/util/tf_graph_transform_util.py:611
↓ 3 callers
Method
get_node_by_name
(self, name: str)
tensorflow_blade/tf_blade/util/simple_graph.py:158
↓ 3 callers
Function
get_node_name
Get node actual name from full name in graph_def connection
tensorflow_blade/tf_blade/util/tf_util.py:49
↓ 3 callers
Function
get_observer_types
( act_ob_ctr: Optional[Callable[..., Observer]], w_ob_ctr: Optional[Callable[..., Observer]],
tools/torch_quant/torch_quant/quantizer.py:82
↓ 3 callers
Function
get_rocm_path
(args)
scripts/python/tao_build.py:74
↓ 3 callers
Method
get_simple_node_by_name
(self, name: str)
tensorflow_blade/tf_blade/util/simple_graph.py:152
↓ 3 callers
Method
get_tensor_info
(self)
tensorflow_blade/tf_blade/util/simple_graph.py:267
↓ 3 callers
Function
git_branch
Get current git branch.
scripts/python/tao_common.py:66
↓ 3 callers
Function
git_head
Get current git HEAD commit.
scripts/python/tao_common.py:72
↓ 3 callers
Function
group_dims
tao_compiler/mlir/xla/ral/context/mkldnn/ideep/ideep/utils.hpp:97
↓ 3 callers
Function
hasSameShape
tao_compiler/mlir/disc/tools/disc-transform/TransformOps/TransformOpsExt.cc:249
↓ 3 callers
Method
has_path
(self, src: int, dst: int)
pytorch_blade/torch_blade/clustering/support_fusion_algorithm.py:46
↓ 3 callers
Function
hash_combine
pytorch_blade/pytorch_blade/compiler/jit/shape_type_spec.cpp:25
↓ 3 callers
Method
hexdigest
return hex representation of digest as string
tao_compiler/mlir/xla/ral/ral_md5.cc:335
↓ 3 callers
Function
insert_prim_constant
pytorch_blade/pytorch_blade/quantization/pybind_functions.cpp:68
↓ 3 callers
Method
isFold
tao_compiler/mlir/disc/transforms/shape_utils.h:109
↓ 3 callers
Method
isFusible
tao_compiler/mlir/disc/transforms/fusion_utils_transform_based.cc:78
↓ 3 callers
Method
isProductEqual
tao_compiler/mlir/disc/transforms/shape_utils.cc:1924
↓ 3 callers
Function
isRowReduction
Returns true if this op is a row reduction.
tao_compiler/mlir/disc/transforms/fusion_utils.cc:460
↓ 3 callers
Method
is_xla_compile_attr_true
If true then the cluster has a XlaCompile=true attribute on one of its nodes.
tao/tao_bridge/passes/tao_mark_for_compilation_pass.cc:213
↓ 3 callers
Method
last_inputs
pytorch_blade/pytorch_blade/compiler/backends/engine_class.cpp:224
↓ 3 callers
Method
last_outputs
pytorch_blade/pytorch_blade/compiler/backends/engine_class.cpp:229
↓ 3 callers
Method
lexical_order_topolist
(self)
pytorch_blade/torch_blade/algorithm/directed_graph.py:54
↓ 3 callers
Function
lowerWithScheduleLoop
we don't do inbound check for kLoop Schedule LoopSplit pass will do this. %num_elements = ElementsIn(root_shape) * loop.for %idx = 0 to %num_element
tao_compiler/mlir/disc/transforms/lhlo_legalize_roots_to_loops.cc:297
↓ 3 callers
Function
ltrim
trim from start (in place)
pytorch_blade/tests/torchscript/shape_analysis_tool.cpp:23
↓ 3 callers
Function
makeDynamicShapeGEMMParamsKey
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.h:214
↓ 3 callers
Function
makeGEMMParamsKey
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.h:177
↓ 3 callers
Function
mergeFusionTag
tao_compiler/mlir/disc/transforms/fusion_utils.cc:269
↓ 3 callers
Function
one_hot
(x, num_classes, dtype=torch.float32)
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/model/modules/utils.py:61
↓ 3 callers
Function
one_of
tao_compiler/mlir/xla/ral/context/mkldnn/ideep/ideep/utils.hpp:72
↓ 3 callers
Method
out_edges
(self, node: int)
pytorch_blade/torch_blade/clustering/support_fusion_algorithm.py:43
↓ 3 callers
Method
parse
tao_compiler/mlir/disc/tools/disc-transform/LinalgExt/LinalgExtOps.cc:557
↓ 3 callers
Function
parseEinsumEquation
tao_compiler/mlir/disc/disc_util.cc:85
↓ 3 callers
Function
parsePDLAttr
tao_compiler/mlir/xla/ral/context/pdll_util.cc:148
↓ 3 callers
Function
parseTransformModuleFromFile
Load transform dialect IR from the given file.
tao_compiler/mlir/disc/tools/disc-transform/utils.cc:79
↓ 3 callers
Function
patch_forward
(old_forward)
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/optimization/utils.py:24
↓ 3 callers
Method
raw_alloc
tao_compiler/mlir/xla/ral/device/gpu/gpu_driver.cc:136
↓ 3 callers
Function
read_bool_from_env
(name, default_val)
scripts/python/tao_common.py:153
← previous
next →
701–800 of 6,088, ranked by callers