onnxruntime
f2dcba7a - Fuse MatMulIntegerToFloat only when scales are scalar (#6008)

Commit
5 years ago
Fuse MatMulIntegerToFloat only when scales are scalar (#6008) MatMulIntegerToFloat fusion fuses per-row and per-column MatMulInteger, which is not supported by the MatMulIntegerToFloat kernel now. Limit the fusion to per-matrix only before we supporting the per-channel fully.
Author
Parents
Loading