sgl-project/sglang · error · ValueError
Model architectures are not supported for now. Supported…
Error message
Model architectures {architectures} are not supported for now. Supported architectures: {all_supported_archs} What it means
The companion error to 1724: none of the requested architectures exist in the registry's supported list, so resolution cannot proceed. The message enumerates all registered architectures so you can see what is available.
Solutions
- Copy the exact architecture string from the model's config.json into the call, or register your architecture with register_model(arch, module:class)
- Check case/spacing against the printed supported list
- If the model lives in the main sglang LLM path rather than multimodal_gen, use the LLM model registry instead
- For a custom model, register it before resolving: registry.register_model('MyArch', 'my_pkg.my_mod:MyModel')
Defensive patterns
Strategy: validation
Validate before calling
supported = set(registry.get_supported_archs())
missing = [a for a in config.architectures if a not in supported]
if missing:
raise ValueError(f'architectures not registered: {missing}; registered: {sorted(supported)}') Type guard
def is_supported(config, registry) -> bool:
return any(a in registry.get_supported_archs() for a in config.architectures) Try / catch
try:
cls = registry.resolve_model_cls(config)
except ValueError as e:
if 'not supported' in str(e):
# fall back to explicit class or different registry
... Prevention
- Validate architectures against get_supported_archs() before building the pipeline
- Register custom architectures at plugin load time
- Watch for architecture renames when upgrading model configs
When it happens
Trigger: Calling inspect_model_cls/resolve_model_cls with a config architectures value like ['MyNewModel'] that was never registered via register_model, or with a typo'd/case-mismatched architecture name.
Common situations: New diffusion/multimodal model not yet added to this registry; HF config using a renamed architecture string; using the multimodal_gen registry for a text-only LLM architecture it does not cover.
Related errors
- Model architectures failed to be inspected. Please check…
- Unsupported model architecture
- Activation function is not supported.
- Can't get gguf config for
- Error raised in subprocess
AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28).
Data as JSON: /api/errors/fe03a82dc72d3eeb.
Report an issue: GitHub.
Appendix: source
Thrown at python/sglang/multimodal_gen/runtime/models/registry.py:352
model = _LazyRegisteredModel(
module_name=split_str[0], class_name=split_str[1]
)
else:
model = _RegisteredModel.from_model_cls(model_cls)
self.registered_models[model_arch] = model
def _raise_for_unsupported(self, architectures: list[str]) -> NoReturn:
all_supported_archs = self.get_supported_archs()
if any(arch in all_supported_archs for arch in architectures):
raise ValueError(
f"Model architectures {architectures} failed "
"to be inspected. Please check the logs for more details."
)
raise ValueError(
f"Model architectures {architectures} are not supported for now. "
f"Supported architectures: {all_supported_archs}"
)
def _try_load_model_cls(self, model_arch: str) -> type[nn.Module] | None:
if model_arch not in self.registered_models:
return None
return _try_load_model_cls(model_arch, self.registered_models[model_arch])
def _try_inspect_model_cls(self, model_arch: str) -> _ModelInfo | None:
if model_arch not in self.registered_models:
return None
return _try_inspect_model_cls(model_arch, self.registered_models[model_arch])
def _normalize_archs(
self,View on GitHub (pinned to 0132848349)