[GGUF FE] Native .gguf graph builder

[mvafin]

Details:

• Part 2 of 2. Adds the native .gguf graph builder: instead of a live GgufDecoder handed over by llama.cpp, read the container directly and build the transformer graph per architecture, emitting nodes in the GGML op vocabulary so both ingest paths share the same op translators. No llama.cpp dependency.
• One generic dense-transformer builder covers the llama family, with per-architecture differences derived from the file itself (q/k norms, qkv biases, rope frequency factors, scalar scales), so most new architectures of that family are just a name in the supported list. MoE routing, muse-glimmer and qwen35's hybrid Gated-DeltaNet stack need real code and have it.
• Also here, because none of it exists until a model can be read from a file:
  • AdaptToGenAI and the tokenizer metadata attached to rt_info, so OpenVINO GenAI can drive the model and build a tokenizer without reopening the file. Neither is reachable from the llama.cpp integration, which owns its own tokenizer and applies its own stateful transformation.
  • MakeStateful's recurrent-state rewrite, for the linear-attention states qwen35 carries. Unlike a KV cache these have no token axis and no SetRows write, so the pairing arrives from the decoder via rt_info.
  • Q4_K integer zero-point: the CPU compressed-FullyConnected fast path is ~2x slower with a fractional f16 zp, which dominates prefill.
  • Per-architecture conversion tests over header-only fixtures generated in CI from llama.cpp, plus a model_hub suite that downloads real checkpoints.
• The frontend stays out of model auto-detection, so core.read_model(".gguf") does not resolve to it; consumers either link it directly or ask for it by name via load_by_framework("gguf").
• Validated on all 25 checkpoints in tests/model_hub_tests/gguf: 25/25 convert, and generation through GenAI matches the per-architecture expectations recorded in docs/supported_models.md. ov_gguf_frontend_tests: 138/138.

Important

Stacked on #37435 (part 1). GitHub only allows a base branch that lives in this repo, so this PR still targets master and its diff therefore includes #37435's commit. Review only the second commit, [GGUF FE] Native .gguf graph builder. It will shrink to that automatically once #37435 merges.

Note

The CPU-side WidenGatherMatmulWeights transformation that MoE expert weights need is intentionally not in this PR and will follow separately; MoE models therefore need that change to compile.

Tickets:

• CVS-188634

AI Assistance:

• AI assistance used: yes
• AI wrote the code and tests. Human-validated by building and running real models rather than trusting the suite: all 25 checkpoints convert, generation was compared against llama.cpp per architecture, and the prefill/zero-point changes were measured end to end.