[GitHub] [incubator-mxnet] pengzhao-intel commented on issue #15862: CPU GEMM in float 16 fails silently with NaiveEngine (CPP api)

pengzhao-intel commented on issue #15862: CPU GEMM in float 16 fails silently with NaiveEngine (CPP api) URL: https://github.com/apache/incubator-mxnet/issues/15862#issuecomment-520817082 > @marekjg I can reproduce this issue from my side when `MXNET_ENGINE_TYPE=NaiveEngine`. But I try to

[GitHub] [incubator-mxnet] pengzhao-intel commented on issue #15862: CPU GEMM in float 16 fails silently with NaiveEngine (CPP api)

pengzhao-intel commented on issue #15862: CPU GEMM in float 16 fails silently with NaiveEngine (CPP api) URL: https://github.com/apache/incubator-mxnet/issues/15862#issuecomment-520816855 > @pengzhao-intel I know it is not supported, problem is from the user point of view with cpp api and

[GitHub] [incubator-mxnet] pengzhao-intel commented on issue #15862: CPU GEMM in float 16 fails silently with NaiveEngine (CPP api)

pengzhao-intel commented on issue #15862: CPU GEMM in float 16 fails silently with NaiveEngine (CPP api) URL: https://github.com/apache/incubator-mxnet/issues/15862#issuecomment-520425796 FP16 in CPU is not supported now. But it should be a problem for the inconsistent error message. W