Implement some custom fb op out variant kernels

[qxy11]

Summary: Implement an out variant version of tbe_input_combine_with_length, offsets_to_lengths, and lenghts_to_offsets, and add a skeleton for custom fb op static kernel dispatch in sigmoid.

Also start adding native kernels (ie. kernels with no out variant but for which we can directly go to the native implementation rather than first going torch torch dispatcher)

Reviewed By: henryoier

Differential Revision: D57453462

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D57453462

[netlify[bot]]

✅ Deploy Preview for pytorch-fbgemm-docs ready!

Name	Link
🔨 Latest commit	4e2180b5321060225c40155ff4a46b297a966ec4
🔍 Latest deploy log	https://app.netlify.com/sites/pytorch-fbgemm-docs/deploys/668ffbc1343a910007222651
😎 Deploy Preview	https://deploy-preview-2793--pytorch-fbgemm-docs.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site configuration.

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D57453462

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D57453462

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D57453462

[facebook-github-bot]

This pull request has been merged in pytorch/FBGEMM@2bd3222ee605aa8cdfa5e459d24ec01c1e257fdd.