[ExecuTorch][WebGPU] test: document bicol decode-GEMV coverage in q4gsw configs

[JulianCloudNTH]

Stack from ghstack (oldest at bottom):

• -> [ExecuTorch][WebGPU] test: document bicol decode-GEMV coverage in q4gsw configs #20598
• [ExecuTorch][WebGPU] q4gsw decode: 2-column "bicol" GEMV (conservative -15..-35% decode latency) #20597

The existing M==1 q4gsw configs (q/kv/gate/down_proj) exercise the new bicol 2-column decode GEMV via the handler's M==1 routing, each reading its own per-column scale across many K-groups. Adds comments to the config tables documenting this and the N % 8 == 0 op constraint -- odd-N is un-exportable through torchao's scale layout, so there is no odd-N config and bicol's has1 odd-N guard is defensive (mirrors coop4's general-N robustness). No new configs.

Differential Revision: D110017691

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20598

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit e2806c4 with merge base b331ebd ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.