Model fails to load when chat template uses HuggingFace generation tags

# Prerequisites - [x] I am running the latest code. - [x] I carefully followed the README.md. - [x] I searched issues and discussions; no existing issue covers this (PR #2082 attempts a fix but is stale and has a missing import). - [x] I reviewed the Discussions. # Expected Behavior `Llama(model_path=...)` should successfully load a GGUF whose embedded `tokenizer.chat_template` contains HuggingFace's `{% generation %}` / `{% endgeneration %}` Jinja tags (e.g. SmolLM3, and any future HF-shipped model adopting the same template extension), even when the caller intends to pass an explicit `chat_format` override. # Current Behavior `Llama.__init__` raises `jinja2.exceptions.TemplateSyntaxError: Encountered unknown tag 'generation'` before the model is usable. The error fires during `Jinja2ChatFormatter.__init__`, which eagerly compiles every chat template found in GGUF metadata regardless of whether the caller will use it. The `{% generation %}` tag is a HuggingFace transformers chat-template extension that marks training-time generation spans for loss masking. It has no inference-time meaning, but jinja2's default environment doesn't recognize it. # Environment and Context - Hardware: Apple M1 Pro, 16 GB - OS: macOS 14.6 (Darwin 23.6.0) - Python: 3.12.9 - llama-cpp-python: main (commit current as of 2025-05-21) - jinja2: 3.x # Failure Information ``` jinja2.exceptions.TemplateSyntaxError: Encountered unknown tag 'generation'. Jinja was looking for the following tags: 'elif' or 'else' or 'endif'. The innermost block that needs to be closed is 'if'. ``` # Steps to Reproduce 1. `pip install llama-cpp-python` 2. `huggingface-cli download bartowski/HuggingFaceTB_SmolLM3-3B-GGUF HuggingFaceTB_SmolLM3-3B-Q4_K_M.gguf` 3. `python -c "from llama_cpp import Llama; Llama(model_path='./HuggingFaceTB_SmolLM3-3B-Q4_K_M.gguf', chat_format='chatml')"` The `chat_format='chatml'` override is intentionally provided to show the failure occurs even when the embedded template would be bypassed: the template is compiled at init regardless. # Related - PR #2082 attempts a fix via a similar Jinja extension but has a missing `nodes` import and incomplete `parse()` body, plus seven months of no reviewer activity. A complete fix is available; will open a PR shortly.