sgl-project/sglang · error · ValueError

No processor registered for architecture: {hf_config.archite

Error message

No processor registered for architecture: {hf_config.architectures}.
Registered architectures: {[model_cls.__name__ for model_cls in PROCESSOR_MAPPING.keys()]}

What it means

get_mm_processor looks up the model architecture in PROCESSOR_MAPPING; an architecture with no registered multimodal processor means SGLang has no MM preprocessing pipeline for that model, so serving it (especially with MM inputs or the rust path) fails.

Source

Thrown at python/sglang/srt/managers/multimodal_processor.py:84

            TransformersAutoMultimodalProcessor,
        )

        return TransformersAutoMultimodalProcessor

    return None


def get_mm_processor(
    hf_config,
    server_args: ServerArgs,
    processor,
    transport_mode,
    model_config=None,
    **kwargs,
) -> BaseMultimodalProcessor:
    processor_cls = get_mm_processor_cls(hf_config, server_args, model_config)
    if processor_cls is None:
        raise ValueError(
            f"No processor registered for architecture: {hf_config.architectures}.\n"
            f"Registered architectures: {[model_cls.__name__ for model_cls in PROCESSOR_MAPPING.keys()]}"
        )
    return processor_cls(hf_config, server_args, processor, transport_mode, **kwargs)

View on GitHub (pinned to 0132848349)

Solutions

1. Upgrade SGLang to a version supporting the architecture
2. Check PROCESSOR_MAPPING keys and register a processor for your architecture
3. Fix the model's config.json architectures to match a supported canonical name
4. Use a supported checkpoint of the same model family

from sglang.srt.managers.multimodal_processor import PROCESSOR_MAPPING
archs = model_config.hf_config.architectures
assert any(a in PROCESSOR_MAPPING for a in archs), f'no MM processor for {archs}'

try:
    get_mm_processor(...)
except ValueError as e:
    if 'No processor registered' in str(e):
        raise SystemExit('upgrade sglang or use a supported checkpoint')
    raise

When it happens

Trigger: Loading a new/unsupported VLM whose hf_config.architectures entry is absent from PROCESSOR_MAPPING; custom model classes with renamed architectures.

Common situations: Newly released VLM on an older SGLang version; community checkpoint with non-standard architecture name; typo in config.json architectures.

Related errors

• SGLANG_RUST_SERVER=1: no native Rust MM pipeline for model_t
• Serve backend {name!r} uses API version {backend.api_version
• {selection_error}{component_suffix}
• No compatible attention backend is available{component_suffi
• Kimi-K3 DCP with decode_attention_backend='cutedsl_mla' requ

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/14920e3c393f2788. Report an issue: GitHub.