Add GGUF support for MiniMax-M2.1 model

[JoursBleu]

What does this PR do?

Add GGUF loading support for MiniMax-M2.1 (456B MoE) model.

MiniMax-M2.1 is a large Mixture-of-Experts model with 456B total parameters (45.9B active), 256 experts and 8 experts per token. This PR enables loading its GGUF-quantized checkpoints (e.g. unsloth/MiniMax-M2.1-GGUF) via from_pretrained(..., gguf_file=...).

Changes

src/transformers/integrations/ggml.py

• Add "minimax-m2" entry to GGUF_CONFIG_MAPPING with model-specific config fields (including MoE fields: expert_count, expert_used_count, expert_feed_forward_length).
• Register GGUFQwen2Converter for minimax_m2 in GGUF_TO_FAST_CONVERTERS (tokenizer is compatible with Qwen2).

src/transformers/modeling_gguf_pytorch_utils.py

• Add MiniMaxM2TensorProcessor class following the new TensorProcessor API introduced in Qwen2/3 MoE + GGUF model support (restored) #42854:
  • preprocess_name(): strips per-expert indices from HF weight names so that multiple experts can map to one fused GGUF tensor.
  • perform_fallback_tensor_mapping(): manually maps MiniMax-M2's w1/w2/w3 expert naming to GGUF's ffn_gate/down/up_exps tensor names, since gguf-py's name_map cannot resolve them.
  • process(): matches GGUF MoE expert tensors and splits them per-expert.
  • _split_moe_expert_tensor(): slices the fused [num_experts, ...] tensor into individual expert weights.
• Register processor in TENSOR_PROCESSORS, add model type and architecture mappings.

Testing

Due to the model size (456B parameters, 227GB for Q8_0 GGUF), no CI-compatible unit tests are included. This is consistent with other large MoE models (e.g., Qwen3-30B-A3B in #42854).

Verified end-to-end on 8×AMD W7900D (48GB each) via vLLM serving the Q8_0 GGUF checkpoint:

• GSM8K 8-shot: 93.7% (official BF16 baseline: 92.0%)
• MMLU 5-shot: 85.66% (official BF16 baseline: 86.2%)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline, Pull Request section?
• Was this discussed/approved via a Github issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the documentation guidelines, and here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR.

@SunMarc @MekkCyber @ArthurZucker

[github-actions]

[For maintainers] Suggested jobs to run (before merge)

run-slow: minimax_m2