is set in compile. The single path execution code does not yet support
        all use cases. We fallback to the existing v1 execution paths if your
        model contains the following:
        1.  `sample_weight_mode` in compile
        2.  `weighted_metrics` in compile
        3.  v1 optimizer
        4.  target tensors in compile If you are experiencing any issues because

operation, and aggressively // unrolls loops. arm64 processes four words at a time. // // It's unclear why the assembly for all other architectures, as well as for // amd64 without ADX, perform better than the compiler output. // TODO(filippo): file cmd/compile performance issue. var supportADX = cpu.X86HasADX && cpu.X86HasBMI2 func init() { if cpu.AMD64 { impl.Register("aes", "ADX", &supportADX) } } //go:noescape func addMulVVW1024(z, x *uint, y uint) (c uint) //go:noescape func addMulVVW1536(z, x *uint,...

operation, and aggressively // unrolls loops. arm64 processes four words at a time. // // It's unclear why the assembly for all other architectures, as well as for // amd64 without ADX, perform better than the compiler output. // TODO(filippo): file cmd/compile performance issue. var supportADX = cpu.X86HasADX && cpu.X86HasBMI2 func init() { if cpu.AMD64 { impl.Register("aes", "ADX", &supportADX) } } //go:noescape func addMulVVW1024(z, x *uint, y uint) (c uint) //go:noescape func addMulVVW1536(z, x *uint,...