---
name: "sglang"

config_file: |
    backend: sglang
    context_size: 8192
    parameters:
      max_tokens: 8192
    function:
      disable_no_action: true
      grammar:
        disable: true
        parallel_calls: true
        expect_strings_after_json: true
    template:
      use_tokenizer_template: true
    # Uncomment to specify a quantization method (optional)
    # quantization: "fp8"
    # Uncomment to set dtype: "auto", "half", "float16", "bfloat16", "float", "float32"
    # dtype: "bfloat16"
    # Uncomment to limit static GPU memory (sglang's mem_fraction_static — analogous to vLLM gpu_memory_utilization)
    # gpu_memory_utilization: 0.75
    # Uncomment to trust remote code from huggingface
    # trust_remote_code: true
    # Uncomment to disable CUDA graph capture (sglang's disable_cuda_graph)
    # enforce_eager: true
    # Uncomment to specify the maximum length of a sequence (sglang's context_length)
    # max_model_len: 32768
    # Uncomment and specify the number of Tensor divisions
    # tensor_parallel_size: 2
    #
    # Anything ServerArgs exposes (~380 fields including speculative
    # decoding, attention backend, MoE/EP, hierarchical cache, …) can be
    # passed verbatim under engine_args:. See
    # https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/server_args.py
    # for the canonical list. Unknown keys fail at load time with a
    # close-match suggestion.
    # engine_args:
    #   speculative_algorithm: EAGLE3
    #   speculative_draft_model_path: lmsys/SGLang-EAGLE3-Llama-3.1-8B-Instruct-SpecForge
    #   speculative_num_steps: 3
    #   speculative_eagle_topk: 4
    #   speculative_num_draft_tokens: 16