Jacques Pienaar
Jacques Pienaar
Should I pull down the other ARM runners?
@dependabot rebase
@dependabot rebase
If it matches https://github.com/openxla/xla/blob/f292b892846960fff42e0e9c11f9a96f22723bd7/xla/mlir_hlo/mhlo/transforms/legalize_to_linalg/legalize_to_linalg.cc#L2924 then it may be an export error (could still be lowering to linalg failure - also the surprised the named Linalg op doesn't have proper defaults...
Is the proposal here that DepthwiseConv2dNative (for different dimensions) has an additional attribute to say that is separable and in which case it gets a rank 1 kernel. And allows...
Could very well be yes. emit-values wasn't changed but could be some overlap in code. Surprised it fails in this manner (on some but not all). I'll try to take...
Re musl libc part, should we defer until that can be checked? And/or easiest way to repro with musl (if related to that PR and musl, I think just repeated...
Same is true for SSP Operation
I don't know SSP and don't know the distinction between auxiliary or not here - I'd have though one could do a variadic operand to all these ops which represent...
Ahhh that's what auxiliary means here. Gotcha. OK, that makes sense. Temporarily disabling would work yes. It is done on verification, but if the tests are disabled then no issues.