[XPU] support bf16 masked_select/grad, expand_v2/grad, paddle_put_along_axis; update bkcl to optimize all2all

[cqulilujia]

PR Category

Custom Device

PR Types

New features

Description

Support bf16 masked_select/grad, expand_v2/grad, paddle_put_along_axis; update bkcl to optimize all2all

[CLAassistant]

All committers have signed the CLA.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 3 committers have signed the CLA.

✅ runzhech
❌ cqulilujia
❌ RuohengMa
_{You have signed the CLA already but the status is still pending? Let us recheck it.}