Add support for zai-org/GLM-4.1V-9B-Thinking

Add support for zai-org/GLM-4.1V-9B-Thinking. When I run:

olive optimize     --model_name_or_path zai-org/GLM-4.1V-9B-Thinking     --precision int4     --output_path models/glm4.1v-thinking

Got:

Loading HuggingFace model from zai-org/GLM-4.1V-9B-Thinking
Traceback (most recent call last):
  File "/usr/local/bin/olive", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/cli/launcher.py", line 68, in main
    service.run()
  File "/usr/local/lib/python3.11/site-packages/olive/cli/optimize.py", line 197, in run
    return self._run_workflow()
           ^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/cli/base.py", line 44, in _run_workflow
    workflow_output = olive_run(run_config)
                      ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/workflows/run/run.py", line 261, in run
    return run_engine(package_config, run_config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/workflows/run/run.py", line 200, in run_engine
    return engine.run(
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/engine/engine.py", line 231, in run
    run_result = self.run_accelerator(
                 ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/engine/engine.py", line 314, in run_accelerator
    output_footprint = self._run_no_search(input_model_config, input_model_id, accelerator_spec, output_dir)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/engine/engine.py", line 358, in _run_no_search
    should_prune, signal, model_ids = self._run_passes(input_model_config, input_model_id, accelerator_spec)
                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/engine/engine.py", line 642, in _run_passes
    model_config, model_id = self._run_pass(
                             ^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/engine/engine.py", line 743, in _run_pass
    output_model_config = host.run_pass(p, input_model_config, output_model_path)
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/systems/local.py", line 45, in run_pass
    output_model = the_pass.run(model, output_model_path)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/passes/olive_pass.py", line 242, in run
    output_model = self._run_for_config(model, self.config, output_model_path)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/passes/pytorch/gptq.py", line 121, in _run_for_config
    wrapper = ModelWrapper.from_model(load_hf_base_model(model, torch_dtype="auto"))
                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/passes/pytorch/train_utils.py", line 126, in load_hf_base_model
    return new_model_handler.load_model(cache_model=False)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/model/handler/hf.py", line 75, in load_model
    model = load_model_from_task(self.task, self.model_path, **self.get_load_kwargs())
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/common/hf/utils.py", line 62, in load_model_from_task
    model = from_pretrained(model_class, model_name_or_path, "model", **kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/olive/common/hf/utils.py", line 94, in from_pretrained
    return cls.from_pretrained(get_pretrained_name_or_path(model_name_or_path, mlflow_dir), **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 603, in from_pretrained
    raise ValueError(
ValueError: Unrecognized configuration class <class 'transformers.models.glm4v.configuration_glm4v.Glm4vConfig'> for this kind of AutoModel: AutoModelForCausalLM.
Model type should be one of ArceeConfig, AriaTextConfig, BambaConfig, BartConfig, BertConfig, BertGenerationConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BitNetConfig, BlenderbotConfig, BlenderbotSmallConfig, BloomConfig, CamembertConfig, LlamaConfig, CodeGenConfig, CohereConfig, Cohere2Config, CpmAntConfig, CTRLConfig, Data2VecTextConfig, DbrxConfig, DeepseekV2Config, DeepseekV3Config, DiffLlamaConfig, DogeConfig, Dots1Config, ElectraConfig, Emu3Config, ErnieConfig, Ernie4_5Config, Ernie4_5_MoeConfig, Exaone4Config, FalconConfig, FalconH1Config, FalconMambaConfig, FuyuConfig, GemmaConfig, Gemma2Config, Gemma3Config, Gemma3TextConfig, Gemma3nConfig, Gemma3nTextConfig, GitConfig, GlmConfig, Glm4Config, Glm4MoeConfig, GotOcr2Config, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTNeoXJapaneseConfig, GptOssConfig, GPTJConfig, GraniteConfig, GraniteMoeConfig, GraniteMoeHybridConfig, GraniteMoeSharedConfig, HeliumConfig, JambaConfig, JetMoeConfig, Lfm2Config, LlamaConfig, Llama4Config, Llama4TextConfig, MambaConfig, Mamba2Config, MarianConfig, MBartConfig, MegaConfig, MegatronBertConfig, MiniMaxConfig, MistralConfig, MixtralConfig, MllamaConfig, ModernBertDecoderConfig, MoshiConfig, MptConfig, MusicgenConfig, MusicgenMelodyConfig, MvpConfig, NemotronConfig, OlmoConfig, Olmo2Config, OlmoeConfig, OpenLlamaConfig, OpenAIGPTConfig, OPTConfig, PegasusConfig, PersimmonConfig, PhiConfig, Phi3Config, Phi4MultimodalConfig, PhimoeConfig, PLBartConfig, ProphetNetConfig, QDQBertConfig, Qwen2Config, Qwen2MoeConfig, Qwen3Config, Qwen3MoeConfig, RecurrentGemmaConfig, ReformerConfig, RemBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, RwkvConfig, SmolLM3Config, Speech2Text2Config, StableLmConfig, Starcoder2Config, TransfoXLConfig, TrOCRConfig, WhisperConfig, XGLMConfig, XLMConfig, XLMProphetNetConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, xLSTMConfig, XmodConfig, ZambaConfig, Zamba2Config.

Reproduce the command and start by tracing model loading through olive/model/handler/hf.py and olive/common/hf/utils.py, then inspect the GPTQ path in olive/passes/pytorch/gptq.py. Determine how the reported Glm4vConfig is handled by the existing loader. Done means the supplied optimization command loads zai-org/GLM-4.1V-9B-Thinking without the AutoModelForCausalLM configuration error.