config_file: |
    backend: dllm
    known_usecases:
        - chat
    parameters:
        # Forwarded to the engine as ctx_len, but the engine at the current
        # pin ignores it - the effective bound is the GGUF's trained context
        # (n_ctx_train, 262144 for this model). Kept for forward-compatibility
        # once the engine honors it. Note dllm generates by denoising whole
        # 256-token canvases, and until the prefix-KV cache lands (dllm P3)
        # EVERY denoise step recomputes the full prompt+canvas, so throughput
        # drops roughly linearly with context occupancy.
        context_size: 4096
    stopwords:
        - <turn|>
    # Templating AND output parsing (content/thought channels, tool calls)
    # are owned by the dllm backend's native gemma4 renderer/parser - NOT
    # llama.cpp's jinja autoparser, so no use_jinja option here.
    # Disabling LocalAI's grammar keeps its generated tool grammar from
    # overriding the backend's native tool-call pipeline (same reasoning as
    # qwen3.yaml / the ds4 importer).
    function:
        grammar:
            disable: true
    template:
        use_tokenizer_template: true
name: diffusiongemma