Skip to content

[docs] Fix QuantizedTensor.from_float examples to use layout name strings #43

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
BhagyeshKothalkar wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[docs] Fix QuantizedTensor.from_float examples to use layout name strings #43

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,11 +29,11 @@ The library provides `QuantizedTensor`, a `torch.Tensor` subclass that transpare
| `TensorCoreMXFP8Layout`| MXFP8 E4M3 | SM ≥ 10.0 (Blackwell) | Block quantization with 32-element blocks, E8M0 scales |

```python
from comfy_kitchen.tensor import QuantizedTensor, TensorCoreFP8Layout, TensorCoreNVFP4Layout
from comfy_kitchen.tensor import QuantizedTensor

# Quantize a tensor
x = torch.randn(128, 256, device="cuda", dtype=torch.bfloat16)
qt = QuantizedTensor.from_float(x, TensorCoreFP8Layout)
qt = QuantizedTensor.from_float(x, "TensorCoreFP8Layout")

# Operations dispatch to optimized kernels automatically
output = torch.nn.functional.linear(qt, weight_qt)
Expand Down
2 changes: 1 addition & 1 deletion comfy_kitchen/tensor/fp8.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ class TensorCoreFP8Layout(QuantizedLayout):

Example:
>>> x = torch.randn(128, 256, device="cuda", dtype=torch.bfloat16)
>>> qt = QuantizedTensor.from_float(x, TensorCoreFP8Layout)
>>> qt = QuantizedTensor.from_float(x, "TensorCoreFP8Layout")
>>> qt.shape
torch.Size([128, 256])
>>> dq = qt.dequantize()
Expand Down