We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent ba8ff36 commit 1b66ea9Copy full SHA for 1b66ea9
quanto/library/ext/README.md
@@ -14,7 +14,7 @@ The operations are defined in `library/ops.py`.
14
15
To provide an implementation for specific device types, use the following syntax:
16
17
-```
+```python
18
@torch.library.impl("quanto_ext::unpack", ["CPU", "CUDA"])
19
def unpack(packed: torch.Tensor, bits: int) -> torch.Tensor:
20
return ext().unpack(t, bits)
quanto/library/python/README.md
@@ -8,7 +8,7 @@ The operations are defined in `library/ops.py`.
8
9
To provide an implementation for an operation, use the following syntax:
10
11
12
@torch.library.impl("quanto_py::unpack", "default")
13
...
0 commit comments