You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardexpand all lines: ReleaseNotes.md
+1-1
Original file line number
Diff line number
Diff line change
@@ -9,7 +9,7 @@ Post-training Quantization:
9
9
- General:
10
10
- ...
11
11
- Features:
12
-
-...
12
+
-(TorchFX, Experimental) Preview support for the new `quantize_pt2e` API has been introduced, enabling quantization of `torch.fx.GraphModule` models with the `OpenVINOQuantizer` and the `X86InductorQuantizer` quantizers. `quantize_pt2e` API utilizes `MinMax` algorithm statistic collectors, as well as `SmoothQuant`, `BiasCorrection` and `FastBiasCorrection` Post-Training Quantization algorithms.
0 commit comments