Highlights
- Enhanced the functionality of Intel® Extension for PyTorch as a backend of
torch.compile: #1568 #1585 #1590 - Fixed the Stable Diffusion fine-tuning accuracy issue #1587 #1594
- Fixed the ISA check on old hypervisor based VM #1513
- Addressed the excessive memory usage in weight prepack #1593
- Fixed the weight prepack of convolution when
padding_modeis not'zeros'#1580 - Optimized the INT8 LSTM performance #1566
- Fixed TransNetV2 calibration failure #1564
- Fixed BF16 RNN-T inference when
AVX512_CORE_VNNIISA is used #1592 - Fixed the ROIAlign operator #1589
- Enabled execution on designated numa nodes with launch script #1517
Full Changelog: v2.0.0+cpu...v2.0.100+cpu