oneapi-src/oneDNN v3.7.1

on GitHub

This is a patch release containing the following changes to v3.7:

• Fixed correctness issue in int8 matmul primitive with int4 weights on on Intel Arc graphics (b16184d)
• Fixed matmul performance regression on Intel Arc graphics (41e406b)
• Fixed potential integer overflow in bf16 convolution for processors with Intel AVX-512 instruction set support (f882861)
• Fixed functional issue in matmul with dropout attribute on generic GPUs (8303330)
• Fixed functional issues in matmul with scales on NVIDIA GPUs (e8d8594)
• Fixed integer overflows for large shapes in convolution for x64 processors (fc3f17a, 31b079f)
• Worked around an MSVC 19.29.30158.0 bug that results in a crash at binary primitive creation on x64 processors (50dd6cc)