Xia Weiwen comments

Results 86 comments of


                                            Xia Weiwen

[Quant] Vectorize scalar remainder in quantized kernel for normalization

Hi there. Please review this PR. Thank you!

[Quant] Vectorize scalar remainder in quantized kernel for normalization

@pytorchbot merge

[Quant] Support lowering of channel shuffle in FX

@vadimkantorov Please review again. Thanks.

[Quant] Support lowering of channel shuffle in FX

> @Xia-Weiwen I'm not a member of PyTorch team, so a review from someone else is required :) I see. Thank you anyway.

[Quant] Support lowering of channel shuffle in FX

Hi @jerryzh168 Could you please review this PR? Or could you ask someone else to review? Thanks!

[Quant] Support lowering of channel shuffle in FX

> channel shuffle should be categorized as copy node I think, so we don't need to add new quantized modules and configs and lowering need to change as well, please...

[Quant] Support lowering of channel shuffle in FX

> could you update the PR summary? Hi @jerryzh168 Sorry for the late reply. It's done. Please review again. Thanks.

[Quant] Support lowering of channel shuffle in FX

Hi @jerryzh168 Please review. Thanks!

[Quant] Support lowering of channel shuffle in FX

Hi @jerryzh168 Please review. Thanks!

[Quant] Support lowering of channel shuffle in FX

Hi @jerryzh168 I changed per your comments. All checks have passed. Do you have more comments? Thanks.