Concat¶
General¶
Concat operation concatenates \(N\) tensors over axis
(here designated \(C\)) and is defined as (the variable names follow the standard Naming Conventions):
where \(c = C_1 + .. + C_{i-1} {}_{} + c'\).
Operation attributes¶
Attribute Name |
De |
|||
---|---|---|---|---|
Specifies dimension along which concatenation happens. |
s64 |
A s64 value in the range of [-r, r-1] where r = rank(src) |
Required |
Execution arguments¶
The inputs and outputs must be provided according to below index order when constructing an operation.
Inputs¶
Index |
Argu |
|
---|---|---|
0 |
|
Required |
Note
At least one input tensor is required. Data types and ranks of all input tensors should match. The dimensions of all input tensors should be the same except for the dimension specified by axis
attribute.
Outputs¶
Index |
Argu |
|
---|---|---|
0 |
|
Required |
Supported data types¶
Concat operation supports the following data type combinations.
Src |
D |
---|---|
f32 |
f32 |
bf16 |
bf16 |
f16 |
f16 |