Xiu-zhe (Roger) Luo
Xiu-zhe (Roger) Luo
@JuliaRegistrator register
@JuliaRegistrator register
@JuliaRegistrator register
I think we would compile instead interpretation when porting real device, since interpretation itself is just not very suitable (and require more work) to make it. I don't think it...
I think this is similar to what I proposed "Array" block before.
1. I don't think we should let it be `broadcastable`, having two similar things `apply!` and `apply!.` is dangerous, especially when a simple for loop will do the job. 2....
I haven't got time to look into the Zygote issue (just traveling Boston), e.g the one @GiggleLiu posted ```julia julia> Zygote.gradient(x->x.content.theta, Daggered(Rx(0.5))) (nothing,) ``` let me take a second look...
No, the benchmark here is mainly to make sure that each block's apply is dispatched to correct function in certain context. The benchmark of instructions is in YaoArrayRegister. So in...
I mean `ConditionBlock`
It's not in YaoBlocks yet. Just remind myself to add it.