Support GLM4 model

[JoeZhang-0x000]

Summary

Split from #332 — add GLM4 causal LM model support only.

Tasks

• Add GLM4 model config adapter (csrc/models/glm4/)
• Add partial rotary support (llama_utils.hpp, llama_attention.*)
• Add forward_naive + GLM4 post-norm support (llama_decoder_layer.*)
• Add RoPE algo selection for GLM4 (llama_model.cpp)
• Add GLM4 special model creation path (rank_worker.cpp)
• Register "glm4" in config_factory.cpp classic_models list
• Register "glm4" in python/infinilm/auto_config.py
• Add GLM4 weight remapping (gate_up_proj split) in modeling_utils.py

Depends on: #348 (Baichuan)
Parent issue: #332