[Diffusion] [BUG] Fix missing initialization of GLM-Image text encoder config

[haojin2]

Motivation

cc @zhaochenyang20

Error in GLM-Image initialization
cmd: sglang serve --model-path zai-org/GLM-Image --backend sglang --num-gpus 1

[02-12 07:44:04] Loading pipeline modules from config: {'_class_name': 'GlmImagePipeline', '_diffusers_version': '0.37.0.dev0', '_name_or_path': 'zai-org/GLM-Image-Decoder', 'text_encoder': ['transformers', 'T5EncoderModel'], 'vision_language_encoder': ['transformers', 'GlmImageForConditionalGeneration'], 'scheduler': ['diffusers', 'FlowMatchEulerDiscreteScheduler'], 'tokenizer': ['transformers', 'ByT5Tokenizer'], 'processor': ['transformers', 'GlmImageProcessor'], 'transformer': ['diffusers', 'GlmImageTransformer2DModel'], 'vae': ['diffusers', 'AutoencoderKL']}
[02-12 07:44:04] Loading required components: ['text_encoder', 'tokenizer', 'vae', 'vision_language_encoder', 'processor', 'transformer', 'scheduler']
Loading required modules:   0%|                                                                                                                                                                                                                                                                                                                                                                                                                                                           | 0/7 [00:00<?, ?it/s][02-12 07:44:04] Loading text_encoder from /workspace/.hf_home/hub/models--zai-org--GLM-Image/snapshots/2c433cc0cbc293bde2ac8ca9624f279b5d23fcf4/text_encoder. avail mem: 87.75 GB
Traceback (most recent call last):
  File "/workspace/sglang/python/sglang/multimodal_gen/runtime/loader/component_loaders/component_loader.py", line 93, in load
    component = self.load_customized(
                ^^^^^^^^^^^^^^^^^^^^^
  File "/workspace/sglang/python/sglang/multimodal_gen/runtime/loader/component_loaders/text_encoder_loader.py", line 205, in load_customized
    return self.load_model(
           ^^^^^^^^^^^^^^^^
  File "/workspace/sglang/python/sglang/multimodal_gen/runtime/loader/component_loaders/text_encoder_loader.py", line 242, in load_model
    model = model_cls(model_config)
            ^^^^^^^^^^^^^^^^^^^^^^^
  File "/workspace/sglang/python/sglang/multimodal_gen/runtime/models/encoders/t5.py", line 574, in __init__
    tp_group = _get_folding_tp_group(config)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/workspace/sglang/python/sglang/multimodal_gen/runtime/distributed/__init__.py", line 64, in _get_folding_tp_group
    if config.parallel_folding:
       ^^^^^^^^^^^^^^^^^^^^^^^
  File "/workspace/sglang/python/sglang/multimodal_gen/configs/models/base.py", line 56, in __getattr__
    raise AttributeError(
AttributeError: 'EncoderConfig' object has no attribute 'parallel_folding'

Modifications

Initialize text_encoder_config to T5Config instead of base Encoder config

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.

Review Process

1. Ping Merge Oncalls to start the PR flow. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments or contact authorized users to do so.
   • /tag-run-ci-label, /rerun-failed-ci, /tag-and-rerun-ci
4. After green CI and required approvals, ask Merge Oncalls to merge.

[gemini-code-assist]

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

[mickqian]

/tag-and-rerun-ci

[hnyls2002]

/tag-and-rerun-ci