fix(minimax): enable autocast on all accelerators in VAE decoding

[li-lizhe]

Fixes #14882

Description: The VAE decode block in the MiniMax H3 modular pipeline only enables fp16 autocast on CUDA devices (enabled=device.type == "cuda"), which disables autocast on other accelerators such as Ascend NPU, Intel XPU, or Apple MPS.

Without autocast on NPU, the VAE decode runs in fp32 (or the tensor's dtype without fp16 acceleration), causing suboptimal performance and potential dtype mismatches when the pipeline expects half-precision computation.

Change:

• enabled=device.type == "cuda" -> enabled=device.type != "cpu"
• Autocast fp16 is now enabled on all accelerator devices while remaining disabled on CPU

Verification on Ascend 910B NPU (torch 2.14.0a0 + torch_npu):

• torch.autocast(device_type="npu", dtype=torch.float16, enabled=True) produces fp16 output (out.dtype=torch.float16)
• torch.autocast(device_type="npu", dtype=torch.float16, enabled=False) produces fp32 output

Notes: (1) end-to-end NPU decode speed-up of this change is not measured - only the dtype path above was checked; (2) CUDA behaviour is unchanged; (3) the branch also carries the get_i2v_mask device-default commit shared with #14765; (4) this is unrelated to the separate CPU/VRAM trade-off discussed in #14746.

[github-actions]

Hi @li-lizhe, thanks for the PR! It does not appear to link an issue it fixes. If this PR addresses an existing issue, please add a closing keyword (e.g. Fixes #1234) to the PR description so the issue is linked. See the contribution guide for more details. If this PR intentionally does not fix a tracked issue, a maintainer can add the no-issue-needed label to silence this reminder.

Please note that PRs without a linked issue are likely to be automatically closed 10 days after this notice.

Once the PR links an issue (or gets the no-issue-needed label), you can ignore this message — it stays here as a comment, but it no longer applies.

[github-actions]

This PR has been automatically closed because it does not link an issue and the reminder above was not addressed within 10 days. If this PR is still relevant, please link the issue it fixes (e.g. Fixes #1234) or ask a maintainer to add the no-issue-needed label, and it can be reopened.

We are experimenting with this process to keep the review queue manageable, and it will sometimes get it wrong. If you think this PR should stay open, please just say so here and we will reopen it — no need to justify it at length.

Thanks again for contributing, and sorry for the noise if we closed this by mistake!

[li-lizhe]

Superseded by #14884 — same commit, unchanged content.

Context: the issue-link reminder bot auto-closed this PR on 2026-09-25 because it had no linked issue, and GitHub refuses to reopen it (REST PATCH /pulls/14766 returns 422 Validation Failed; GraphQL reopenPullRequest returns Could not open the pull request.) even though the fork and the head branch still exist and point at this PR's head commit. The replacement PR links the tracked issue, so the reminder no longer applies.