mamba2: remove hardcoded 2x expansion factor and invalid d_inner % d_state check

[limloop]

This PR removes two unnecessary restrictions in Mamba2 that prevent loading models with custom architectures.

Changes:

1. Remove hardcoded 2x expansion factor (GGML_ASSERT(2 * n_embd == d_inner))

   • The assert assumed all Mamba2 models have expand=2
   • expand is not stored in GGUF, only d_inner is
   • Removing it allows models with any expansion factor (1, 2, 3, etc.)

2. Remove invalid d_inner % d_state check

   • In Mamba2, d_inner and d_state are unrelated parameters
   • This assert has no architectural justification for Mamba2

Testing:

• ✅ Default Mamba2 (expand=2) — loads and runs correctly
• ✅ Custom model (expand=1, d_inner=512, d_model=512) — loads and generates coherent output

Backward compatibility: Models with expand=2 work identically to before.

Related discussion: #21346

[ggml-gh-bot]

Hi @limloop, thanks for your contribution!

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

• AI-generated content: This project does not accept PRs, descriptions or commit messages that are fully or predominantly AI-generated. If you have used AI to assist you in writing code, please make sure to disclose that explicitly.

---

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

[CISC]

Do you have links to models with differing expand?

[limloop]

@CISC, here's a model with non-standard expand:

limloop/whiff-mamba2-50M-v0.1
https://huggingface.co/limloop/whiff-mamba2-50M-v0.1

Config values:

• expand = 1
• d_model = 512
• d_inner = 512 (computed as expand * d_model)

With current llama.cpp (the hardcoded 2 * n_embd == d_inner assert), this model fails to load.

With my changes (this PR), it loads and generates coherent text.

[CISC]

Thanks, rebase and adjust accordingly to refactor please (moved to conversion/mamba.py).

[limloop]

@CISC updated, ready for review

[CISC]

Sorry for the long delay, I had hoped @compilade would take a look.