model : fix k-pool indexer softmax gridDim.y overflow

[AIalliAI]

Overview

Reshape k-pool gate logits before ggml_soft_max so n_new does not map to gridDim.y, which is capped at 65535 on CUDA. During k-pool indexer prefill at n_kv >= 262144, the gate softmax is shaped [kpool, head_dim, n_new] and trips the launch at kpool = 4.

Reshape to [kpool, head_dim * n_new] before softmax, reshape back after. Same pattern as the comment in qwen4exp.cpp.

Depends on #27773. Review the scoped 2-commit diff here:
timkhronos:GLM5.3-Flash...AIalliAI:fix/glm5-kpool-softmax-grid-y

Intended merge path: timkhronos#11 into GLM5.3-Flash, then #27773 to master. Do not merge this PR directly to master.

Additional information

Related: #27754, unslothai#214, #27901, #28175

Fork copies: timkhronos#11, AIalliAI#2

Requirements

• I have read and agree with the contributing guidelines
• AI usage disclosure: YES - assisted implementation and review; I understand the change and can maintain it.

[ggml-gh-bot]

Hi @AIalliAI, thanks for your contribution!

Per our contribution guidelines, the automated PR checker found the following issue(s) that need your attention:

• Multiple open PRs from a new contributor: We limit new contributors (those without a previously merged PR) to 1 open PR at a time. You currently have 2 open PRs.

• Large PR: Large changes require prior discussion (e.g. an issue or RFC) and maintainers may not be able to review this PR as-is. Consider splitting it into smaller, focused PRs.

---

Please note that maintainers reserve the right to make final decisions on PRs. If you believe there is a mistake, please comment below.

[AIalliAI]

Hi @AIalliAI, thanks for your contribution!

Per our contribution guidelines, the automated PR checker found the following issue(s) that need your attention:

• Multiple open PRs from a new contributor: We limit new contributors (those without a previously merged PR) to 1 open PR at a time. You currently have 2 open PRs.
• Large PR: Large changes require prior discussion (e.g. an issue or RFC) and maintainers may not be able to review this PR as-is. Consider splitting it into smaller, focused PRs.

Please note that maintainers reserve the right to make final decisions on PRs. If you believe there is a mistake, please comment below.

As I've replied on the other comments you made. Your instructions are conflicting and I will be combining all of these int one pr to support GLM5. @maintainers